
Christopher OlahResearcher
Anthropic
Co-founder
via Anthropic
Researcher · Engineer
Member of Technical Staff at Anthropic
Gorton studies mechanistic interpretability—methods for understanding what neural networks represent internally. After helping establish Goodfire's research program, she joined Anthropic's Cognitive Oversight team, which investigates how advanced models can be made more trustworthy.
See something inaccurate or outdated?
Anthropic
GoodfireWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Last editorial review: August 8, 2026