© 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. 26362
    Prev
    Next
    INDEX
    Explanations

    Ellipse equations

    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
     Bass
    -0.08
     Plus
    -0.08
    agas
    -0.08
     Pension
    -0.08
    按钮
    -0.08
     حاج
    -0.07
    紧
    -0.07
    Bass
    -0.07
    ifun
    -0.07
     ಕಳೆದ
    -0.07
    POSITIVE LOGITS
     coordinates
    0.10
    coordinates
    0.09
     Coordinates
    0.09
     calculus
    0.08
    лощад
    0.08
     speciaal
    0.08
     coords
    0.08
    พู
    0.08
    Coordinates
    0.08
    _coordinates
    0.08
    Activations Density 0.044%

    No Known Activations