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. 111956
    Prev
    Next
    INDEX
    Explanations

    得

    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
     அல்ல
    -0.10
     இல்லை
    -0.08
     compositions
    -0.08
     என்று
    -0.08
     заранее
    -0.08
     inward
    -0.08
    !:
    -0.08
     இய
    -0.08
     завер
    -0.07
     モ
    -0.07
    POSITIVE LOGITS
     bing
    0.08
    .Bounds
    0.08
    玩
    0.08
    ल्प
    0.08
    ుప
    0.08
    through
    0.08
    ен
    0.08
    acebook
    0.07
     Regen
    0.07
    ിലും
    0.07
    Activations Density 0.000%

    No Known Activations