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. 330
    Prev
    Next
    INDEX
    Explanations

    design descriptions

    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
    .contrib
    -0.09
     medic
    -0.08
    inguished
    -0.08
     Collaborative
    -0.07
     الجنوبية
    -0.07
     embryo
    -0.07
    �
    -0.07
    FY
    -0.07
    mig
    -0.07
     राज्यों
    -0.07
    POSITIVE LOGITS
    חה
    0.09
    强调
    0.08
     elements
    0.08
    ,比如
    0.08
    ạo
    0.08
     강조
    0.08
    _elements
    0.08
    ,如
    0.08
    ,包括
    0.07
     emphasize
    0.07
    Activations Density 0.010%

    No Known Activations