© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8101
    Prev
    Next
    INDEX
    Explanations

    math inner product

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Summary
    -0.09
    -summary
    -0.08
     лоз
    -0.08
     vapor
    -0.08
     ethanol
    -0.08
    _summary
    -0.08
     Summary
    -0.08
     вов
    -0.08
    Automation
    -0.08
     техники
    -0.07
    POSITIVE LOGITS
     canonical
    0.10
    canonical
    0.09
    칙
    0.09
     canon
    0.09
     enjoys
    0.09
     induced
    0.09
     induces
    0.08
     juge
    0.08
     Leb
    0.08
     cuad
    0.08
    Activations Density 0.016%

    No Known Activations