© 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. 47120
    Prev
    Next
    INDEX
    Explanations

    memory

    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
    通知
    -0.08
     порт
    -0.08
     стол
    -0.07
    座
    -0.07
    庄
    -0.07
    oting
    -0.07
     кер
    -0.07
    _star
    -0.07
     выполнение
    -0.07
    (Column
    -0.07
    POSITIVE LOGITS
     capabilities
    0.10
     abilities
    0.09
    (saved
    0.09
     забы
    0.08
    irika
    0.08
     تحقی
    0.08
    stücke
    0.08
    ிமுக
    0.08
     trauma
    0.08
    忆
    0.08
    Activations Density 0.013%

    No Known Activations