© 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. 44770
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    iste
    -0.07
    Estado
    -0.07
     Diário
    -0.07
     experimentally
    -0.07
     estimation
    -0.07
    Uma
    -0.07
     genommen
    -0.07
    年轻
    -0.07
    estim
    -0.07
     Jalan
    -0.07
    POSITIVE LOGITS
    -specific
    0.08
     ayrı
    0.08
     Specialists
    0.08
    _special
    0.08
     membership
    0.08
    _specific
    0.08
    専
    0.08
     spécialisés
    0.08
     Membership
    0.08
     spezial
    0.08
    Activations Density 0.034%

    No Known Activations