© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 71491
    Prev
    Next
    INDEX
    Explanations

    a

    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
     drogas
    -0.08
     tulee
    -0.08
    urt
    -0.08
     جذب
    -0.08
    urlar
    -0.08
     Hib
    -0.08
    овали
    -0.08
    stoffen
    -0.08
    Capture
    -0.08
    ாட்டு
    -0.08
    POSITIVE LOGITS
     الرياضية
    0.08
     expressions
    0.07
     Expressions
    0.07
     arithmetic
    0.07
     maple
    0.07
     કુલ
    0.07
    _expression
    0.07
     decre
    0.07
    poner
    0.07
     العدد
    0.07
    Activations Density 0.003%

    No Known Activations