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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64036
    Prev
    Next
    INDEX
    Explanations

    chess

    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
    <HTML
    -0.08
     waving
    -0.08
    angezien
    -0.08
    Mitt
    -0.08
     waypoint
    -0.07
     minst
    -0.07
    altung
    -0.07
    网页版
    -0.07
     glitch
    -0.07
    ipad
    -0.07
    POSITIVE LOGITS
     лав
    0.09
    0.08
     ход
    0.08
     Worked
    0.07
     Я
    0.07
     Abs
    0.07
     FO
    0.07
     ingles
    0.07
    _man
    0.07
     everyone
    0.07
    Activations Density 0.001%
    No Known Activations