© 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. 65469
    Prev
    Next
    INDEX
    Explanations

    error messages debugging

    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
    calendar
    -0.08
     Kalender
    -0.08
    ifestyle
    -0.08
     dynasty
    -0.08
     Dynasty
    -0.08
    commodation
    -0.08
    -story
    -0.08
    servative
    -0.08
    .calendar
    -0.08
    afstand
    -0.08
    POSITIVE LOGITS
    Error
    0.17
     error
    0.17
    错误
    0.17
    _error
    0.15
     오류
    0.15
    (errors
    0.15
    .error
    0.15
    	error
    0.15
    (error
    0.15
     errors
    0.15
    Activations Density 0.021%

    No Known Activations