© 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. 78392
    Prev
    Next
    INDEX
    Explanations

    delimiters/formatting/non-english

    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
     відпов
    -0.08
    129
    -0.08
    _delivery
    -0.07
    _urls
    -0.07
     mn
    -0.07
     URLs
    -0.07
    _car
    -0.07
    estr
    -0.07
    abag
    -0.07
     richi
    -0.07
    POSITIVE LOGITS
     kilo
    0.08
    waardige
    0.08
    niers
    0.08
    ుకుంది
    0.08
    与此同时
    0.08
     Broncos
    0.08
    yscy
    0.07
     réflexion
    0.07
     cyd
    0.07
     reflux
    0.07
    Activations Density 0.001%

    No Known Activations