© 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. 43571
    Prev
    Next
    INDEX
    Explanations

    data and measurements

    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
     Arme
    -0.08
    Adobe
    -0.08
    Guys
    -0.07
    ивание
    -0.07
     Keith
    -0.07
     establishment
    -0.07
    dry
    -0.07
    Wait
    -0.07
    _Cell
    -0.07
     Cell
    -0.07
    POSITIVE LOGITS
    COD
    0.09
    DQ
    0.09
    ン
    0.09
    ERG
    0.08
    DG
    0.08
     extender
    0.08
     salar
    0.08
    ER
    0.08
    PQ
    0.08
     SUBSTITUTE
    0.08
    Activations Density 0.000%

    No Known Activations