© 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. 129349
    Prev
    Next
    INDEX
    Explanations

    back

    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
    ורס
    -0.07
     recurrent
    -0.07
    .cash
    -0.07
     friends
    -0.07
     vitaminas
    -0.07
     curs
    -0.07
     aute
    -0.07
    kir
    -0.07
     Likewise
    -0.07
     Kir
    -0.07
    POSITIVE LOGITS
    束
    0.09
     순간
    0.08
    _MINUS
    0.08
    _adapter
    0.08
    까지
    0.07
    _OF
    0.07
    瞬
    0.07
    -minus
    0.07
     gard
    0.07
    azzo
    0.07
    Activations Density 0.013%

    No Known Activations