© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78497
    Prev
    Next
    INDEX
    Explanations

    usability

    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
    duplicates
    -0.07
    巨
    -0.07
    牌
    -0.07
     gifts
    -0.07
    _emit
    -0.07
    to
    -0.07
    .lua
    -0.07
     bă
    -0.07
    州
    -0.07
    .to
    -0.07
    POSITIVE LOGITS
     ergonomic
    0.09
     Jakob
    0.09
    Jer
    0.09
     Jer
    0.08
     vict
    0.08
     satisfacción
    0.08
     Logitech
    0.08
     meur
    0.08
     arvio
    0.08
    Princip
    0.08
    Activations Density 0.008%

    No Known Activations