© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65524
    Prev
    Next
    INDEX
    Explanations

    I

    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
     الإسرائيلي
    -0.09
    刑
    -0.09
     NATO
    -0.08
     diplomatic
    -0.08
     اسرائی
    -0.08
    resent
    -0.08
    väl
    -0.08
     agentes
    -0.08
     Charter
    -0.08
    代理
    -0.08
    POSITIVE LOGITS
    _recipe
    0.13
     рецеп
    0.13
     Recipes
    0.13
     Pinterest
    0.12
     Recipe
    0.12
    (recipe
    0.12
    Recipes
    0.12
    recipe
    0.12
     recipe
    0.12
    .recipe
    0.12
    Activations Density 0.343%

    No Known Activations