© 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. 26539
    Prev
    Next
    INDEX
    Explanations

    Calligraphy

    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
    lebn
    -0.09
    որդ
    -0.08
     zahlen
    -0.08
     Legisl
    -0.08
     reimbursement
    -0.08
     emitting
    -0.08
    等奖
    -0.08
    183
    -0.08
    orneq
    -0.08
     legisl
    -0.08
    POSITIVE LOGITS
     serif
    0.11
     스타일
    0.10
    Tahoma
    0.10
     стиль
    0.10
    Italic
    0.10
     Styles
    0.10
     стиле
    0.09
     estilos
    0.09
     styles
    0.09
     शैली
    0.09
    Activations Density 0.009%

    No Known Activations