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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113902
    Prev
    Next
    INDEX
    Explanations

    Text alerts

    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
     releg
    -0.07
    /js
    -0.07
     */↵
    -0.07
    `;↵
    -0.07
    人的
    -0.07
     dunk
    -0.07
    `;↵↵
    -0.07
     укра
    -0.06
    Importance
    -0.06
    谁
    -0.06
    POSITIVE LOGITS
     verzoek
    0.09
    Entered
    0.09
    即可
    0.09
    ahayag
    0.09
    ıll
    0.08
     magnet
    0.08
     suffit
    0.08
    анды
    0.08
     Magnet
    0.08
    ltre
    0.08
    Activations Density 0.010%

    No Known Activations