© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75711
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     linguagem
    -0.08
    ראת
    -0.08
     להז
    -0.08
    String
    -0.08
    -0.08
     لگا
    -0.08
    גישה
    -0.07
    字符串
    -0.07
    irí
    -0.07
     לא
    -0.07
    POSITIVE LOGITS
     matr
    0.07
     phil
    0.07
     contribute
    0.07
     matric
    0.07
     minorities
    0.07
    fragment
    0.07
    }'
    0.07
     pulm
    0.07
    Accounts
    0.07
     cuadros
    0.07
    Activations Density 0.055%
    No Known Activations