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. 77235
    Prev
    Next
    INDEX
    Explanations

    Forest

    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
     bicarbon
    -0.08
     кич
    -0.08
     úd
    -0.08
     khác
    -0.08
     carriage
    -0.08
     residue
    -0.07
     jealousy
    -0.07
     grace
    -0.07
     Hale
    -0.07
     energet
    -0.07
    POSITIVE LOGITS
    .Random
    0.10
    随机
    0.10
    Forest
    0.09
     랜
    0.09
    总统
    0.08
    Random
    0.08
    (Random
    0.08
     Random
    0.08
     ভোট
    0.08
     forêt
    0.08
    Activations Density 0.002%

    No Known Activations