Howdy! I'm Rohan. I'm a computer science student at Northeastern University, concentrated in artificial intelligence. I work on mechanistic interpretability: the field of research dedicated to understanding the internal computations of AI models.

I'm currently a research fellow with the Bau Lab, through the Cambridge–Boston Alignment Initiative. I've previously worked with Northeastern's Research in AI Lab on cross-layer superposition, and with Goodfire on understanding evaluation awareness in language models.

My email is [email protected]. All of my code can be found on my GitHub. You can also find me on Twitter @rollingro11 and LinkedIn.