© 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. 110009
    Prev
    Next
    INDEX
    Explanations

    extend

    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
    Negative Logits
    (android
    -0.09
     ತಿಳ
    -0.08
     يعرف
    -0.08
    روفة
    -0.07
     وكذلك
    -0.07
     coneg
    -0.07
     courant
    -0.07
     Ro
    -0.07
     teada
    -0.07
     serta
    -0.07
    POSITIVE LOGITS
    hren
    0.07
    enge
    0.07
     basalt
    0.07
    bbb
    0.07
     villas
    0.07
    Balls
    0.07
    515
    0.07
    shan
    0.07
     iluminación
    0.07
     Wiel
    0.07
    Activations Density 0.000%

    No Known Activations