© 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. 47288
    Prev
    Next
    INDEX
    Explanations

    в

    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
    -effect
    -0.07
    fillment
    -0.07
     beroeps
    -0.07
     lid
    -0.07
    portfolio
    -0.07
     кү
    -0.07
    HAS
    -0.07
    luit
    -0.07
    ennium
    -0.07
    noi
    -0.07
    POSITIVE LOGITS
     plais
    0.08
    vidia
    0.08
     kli
    0.08
    δήποτε
    0.07
     Iron
    0.07
    Iron
    0.07
    誰
    0.07
    ექ
    0.07
    Pun
    0.07
     disguis
    0.07
    Activations Density 0.039%

    No Known Activations