Life Story

I grew up in Singapore and went to Raffles Girls' School & Raffles Institution. During high school I mostly occupied myself with physics (IPhO) and later astronomy (IOAA) competitions. I also spent a lot of time on physics research through IYPT (or OYPT) which is a great program. These allowed me to go to some pretty life-changing camps like SIYSS and Atlas. Unrelated to work I was also in the SNYO which was super fun.

I then went to MIT and decided to major in physics. The summer after freshman year, I did MISTI at the University of Pisa in Italy (super fun). At the beginning of sophomore year I got into AI interpretability, thanks to my GOAT advisor Max Tegmark. I was also a MATS 8.0 scholar under Neel Nanda. This was a 10/10 program and something I highly recommend for anyone looking to get into AI safety.

Currently I'm a junior. This summer I will be interning at Jump as a QR, and I'm thinking about post-graduation plans.

Recently

• [2026.02.23] I spent January 2026 in London doing the MATS Extension! Started on a project about model values during post-training, will continue working on this during the semester.
• [2026.02.23] This spring at MIT I am finishing my graduation requirements. We'll see what happens next.

Music

My music taste is objectively the best in the world, so here are some amazing playlists.

Travel / Photography

I love traveling and experiencing new places and things. Fun fact, since Aug 2023 when I started at MIT, I've flown 57 flights for a total distance of 7.3x around the world, although a lot of that is just going home (BOS-SIN is brutal) or work-related stuff.

I like taking pictures. Most of these are taken with a Canon EOS R50, more on my Instagram.

‹

›

Research Interests

Models should be aligned with what we want them to be. To me this means 1. being able to interpret what they're doing and 2. being able to shape them intentionally.

First-Author Publications

Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit

N Jiang*, X Sun*, L Dunlap, L Smith, N Nanda

NeurIPS 2025 Mech Interp Workshop (Spotlight) - arXiv:2512.10092

SAEs may or may not be useful for interpreting models, but we think they are useful for interpreting (text) data. We explore the use of SAEs as effectively a data labeller.

Dense SAE Latents Are Features, Not Bugs

X Sun*, A Stolfo*, J Engels, B Wu, S Rajamanoharan, M Sachan, M Tegmark

NeurIPS 2025 - arXiv:2506.15679

Some features in SAEs occur very frequently. We look into these features, finding that they often correspond to true high-frequency model signals.

The effects of projection on the splashback feature

X Sun, S O'Neil, X Shen, M Vogelsberger

The Open Journal of Astrophysics 2025 8 (July). - arXiv:2503.04882

The boundaries of galaxy halos are fuzzy, and observations differ from simulations. We investigate the effects of projection on measuring this boundary.

Other Publications

The Geometry of Concepts: Sparse Autoencoder Feature Structure

Y Li*, EJ Michaud*, DD Baek*, J Engels, X Sun, Max Tegmark

Entropy 27 (4), 344 - arXiv:2410.19750

When I first joined Tegmark's group, I helped out with this project, showing how SAE feature geometry reflects semantic structure.

Performance and Plume Characterization of the MUlti–Stage Ignition Compact (MUSIC) Hall Effect Thruster

GC Potrivitu, M Laterza, D Agarwal, X Sun, JWM Lim

Proceedings of the 38th International Electric Propulsion Conference 2024 - ResearchGate

I interned at Aliena after high school and worked on characterizing a small Hall effect thruster.