© 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. 30975
    Prev
    Next
    INDEX
    Explanations

    touch

    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
     combustível
    -0.09
    ثل
    -0.08
     recurrence
    -0.08
     حساب
    -0.08
     reprez
    -0.08
    æðum
    -0.08
    .Foreign
    -0.08
     daş
    -0.08
     drivetrain
    -0.08
    Mobil
    -0.08
    POSITIVE LOGITS
    empty
    0.10
     Creation
    0.10
    _creation
    0.10
     创建
    0.09
     empty
    0.09
    .empty
    0.09
    (empty
    0.09
     nonexistent
    0.09
     creation
    0.09
    不存在
    0.09
    Activations Density 0.004%

    No Known Activations