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. 90237
    Prev
    Next
    INDEX
    Explanations

    geometry problems

    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
     جامعه
    -0.09
     വ്യ
    -0.08
     Scandinavian
    -0.08
     hygiene
    -0.08
     انواع
    -0.07
     הש
    -0.07
     empleo
    -0.07
    rie
    -0.07
    ЕН
    -0.07
     Scandin
    -0.07
    POSITIVE LOGITS
    Coordinates
    0.10
     coordinates
    0.09
    (vertices
    0.09
    .coordinates
    0.09
    coordinates
    0.09
     Coordinates
    0.08
    Coords
    0.08
    Verification
    0.08
     координ
    0.08
    _coords
    0.08
    Activations Density 0.042%

    No Known Activations