Chris Olah / Anthropic — AI Researcher

**Chris Olah** is a co-founder of **Anthropic** and the head of its **Interpretability** team. He is the pioneer of **mechanistic interpretability** — the field of reverse-engineering neural networks to understand exactly what they're doing internally, neuron by neuron, circuit by circuit. He has no PhD and no traditional academic credentials — he is entirely self-taught, which gives him a distinctive outsider's perspective that has proven extraordinarily productive.