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. 90681
    Prev
    Next
    INDEX
    Explanations

    adjacency of points

    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
    ricorn
    -0.08
    antage
    -0.08
     metus
    -0.08
     (%)
    -0.08
    _ACCEL
    -0.07
     reform
    -0.07
    وير
    -0.07
     оцен
    -0.07
     exports
    -0.07
     시
    -0.07
    POSITIVE LOGITS
     consecutive
    0.12
     Conse
    0.10
    secutive
    0.09
    _gap
    0.09
     interven
    0.09
     spacing
    0.09
     промеж
    0.09
     consecut
    0.09
     अंतर
    0.09
    prung
    0.09
    Activations Density 0.025%

    No Known Activations