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. 11600
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     spool
    -0.08
     Goldman
    -0.08
    人民币
    -0.08
     freeway
    -0.08
     omi
    -0.08
    amboo
    -0.08
    طة
    -0.07
     Jean
    -0.07
     Reconstruction
    -0.07
     squeezed
    -0.07
    POSITIVE LOGITS
    _sync
    0.08
     electroph
    0.08
    _course
    0.08
    Dance
    0.08
     значение
    0.08
     isikhathi
    0.07
     полез
    0.07
     사항
    0.07
    Sync
    0.07
    .course
    0.07
    Activations Density 0.012%

    No Known Activations