Karthik Viswanathan

I am a final-year PhD student at the University of Amsterdam in the Institute of Physics, working on the interpretability of large language models application. Prior to this, I was working on analyzing the large scale structure of the universe using topological data analysis.

My interdisciplinary journey began with competitive programming, progressed through developing machine learning models as a surveillance analyst at Goldman Sachs, and was enriched during my master’s in theoretical physics. My cross-domain exposure has allowed me to transition smoothly across disciplines, enabling meaningful contributions to both practical implementations and theoretical investigations in scientific research.

I’m currently seeking research roles in AI interpretability and safety. If you feel my background would be a good fit, please feel free to email me.

news

Jul 17, 2025	I’m attending ICML 2025, where I’ll be presenting some of my recent work on interpretability in large language models: Conference: Persistent Topological Features in Large Language Models Workshop on High-Dimensional Learning Dynamics: Probing Geometry of Next Token Prediction Using Cumulant Expansion of the Softmax Entropy
Jul 10, 2025	I’m participating in MARS 3.0 (Mentorship for Alignment Research Students), a research program run by the Cambridge AI Safety Hub. As part of this program, I will be working alongside a group of talented researchers on problems related to Chain-of-Thought reasoning in AI systems.
May 27, 2025	Workshop Announcement: Interpretability in LLMs using Geometric and Statistical Methods I am organizing a workshop taking place on May 27-28 where we will explore recent developments in interpretability for large language models (LLMs) using geometric and statistical methods. For further details, check out the workshop page.