© 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. 48026
    Prev
    Next
    INDEX
    Explanations

    Brocard points in geometry

    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
     Dom
    -0.09
     dom
    -0.08
     Monde
    -0.08
    duk
    -0.08
     dager
    -0.08
     Calc
    -0.08
     verantwoordelijkheid
    -0.08
     dome
    -0.08
     efforts
    -0.08
    Dom
    -0.07
    POSITIVE LOGITS
    uration
    0.07
    _plus
    0.07
    URATION
    0.07
    /popper
    0.07
     posts
    0.07
    ospatial
    0.07
    Vice
    0.07
     Parsed
    0.07
     directory
    0.07
     bootstrap
    0.07
    Activations Density 0.000%

    No Known Activations