© 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. 95423
    Prev
    Next
    INDEX
    Explanations

    序

    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
    措施
    -0.08
     masks
    -0.08
     fragile
    -0.08
    .shopping
    -0.08
    -mask
    -0.08
    _ENUM
    -0.07
    (mask
    -0.07
     kamp
    -0.07
     mask
    -0.07
    授
    -0.07
    POSITIVE LOGITS
    Temporal
    0.11
     Temporal
    0.10
     저장
    0.10
     storing
    0.10
     хранения
    0.10
     temporal
    0.10
     хран
    0.09
    Hourly
    0.09
     chrono
    0.09
     기록
    0.09
    Activations Density 0.004%

    No Known Activations