Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11998
    Prev
    Next
    INDEX
    Explanations

    detect

    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
     interpersonal
    -0.08
     unjust
    -0.07
     articul
    -0.07
    福
    -0.07
     etched
    -0.07
    -0.07
    వ
    -0.07
     mars
    -0.07
     justice
    -0.07
     perspectivas
    -0.07
    POSITIVE LOGITS
     detects
    0.13
     automatiquement
    0.13
    .detect
    0.12
     déterminer
    0.12
     bepalen
    0.12
     판단
    0.12
     automáticamente
    0.12
     判断
    0.11
     Detect
    0.11
     automatisch
    0.11
    Activations Density 0.020%

    No Known Activations