Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102694
    Prev
    Next
    INDEX
    Explanations

    Multiply

    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
     summit
    -0.08
     ethnic
    -0.08
     Summit
    -0.08
     Cannon
    -0.07
    rance
    -0.07
     bear
    -0.07
     predominantly
    -0.07
     역시
    -0.07
     bipolar
    -0.07
    bije
    -0.07
    POSITIVE LOGITS
    /div
    0.09
    人为
    0.07
    Anyway
    0.07
    訳
    0.07
     вперед
    0.07
     भार
    0.07
    _into
    0.07
    আ
    0.07
    债
    0.07
    展开
    0.07
    Activations Density 0.019%

    No Known Activations