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. 119160
    Prev
    Next
    INDEX
    Explanations

    new

    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
     aust
    -0.08
     Shame
    -0.08
     auster
    -0.08
     violin
    -0.08
     بايد
    -0.08
     ved
    -0.07
     Weih
    -0.07
    Tr
    -0.07
     Sug
    -0.07
     pitäisi
    -0.07
    POSITIVE LOGITS
    -connect
    0.08
     ನೀಡಿದ್ದಾರೆ
    0.08
    ಿಕ
    0.08
    ';
    ↵
    ↵
    0.08
    owel
    0.08
    icane
    0.08
    ";
    ↵
    ↵
    0.07
     Interaction
    0.07
    _CONNECT
    0.07
    orange
    0.07
    Activations Density 0.000%

    No Known Activations