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. 46159
    Prev
    Next
    INDEX
    Explanations

    policy violations

    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
     확보
    -0.09
     мастер
    -0.09
    AVAILABLE
    -0.09
     لاہور
    -0.09
     AVAILABLE
    -0.08
     maestro
    -0.08
     firmado
    -0.08
     alumn
    -0.08
    Optimal
    -0.08
     ছাড়
    -0.08
    POSITIVE LOGITS
     pornography
    0.11
     prohibited
    0.10
     porn
    0.10
    は禁止
    0.10
    违法
    0.09
     Examples
    0.09
    违反
    0.09
     extrad
    0.09
     outright
    0.08
     illegal
    0.08
    Activations Density 0.029%

    No Known Activations