Kaushik Reddy

I’m a researcher working on AI safety and mechanistic interpretability — trying to understand how neural networks represent and process information internally, so we can build AI systems that are transparent and trustworthy.

Previously I worked on [filler: past role or lab], and studied [filler: degree, university]. Outside research I [filler: a line with some personality — climbing, cooking, chess].

The best ways to reach me are email — kr.reddy.kaushik@gmail.com — or X.

Use this link to give me anonymous /feedback.