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. 55099
    Prev
    Next
    INDEX
    Explanations

    Days

    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
     enlight
    -0.08
     enlightened
    -0.08
     spe
    -0.07
    文明
    -0.07
    形
    -0.07
     secur
    -0.07
     Literal
    -0.07
    792
    -0.07
    /url
    -0.07
    .literal
    -0.07
    POSITIVE LOGITS
    Workout
    0.11
     workouts
    0.11
    日に
    0.11
     alternating
    0.11
     Workout
    0.11
     workout
    0.11
     bodybuilding
    0.11
     treino
    0.10
     sábado
    0.10
     ہفت
    0.10
    Activations Density 0.007%

    No Known Activations