© 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. 23-RESID-POST-AA
    11. 52217
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     આંત
    -0.08
     resources
    -0.07
     заст
    -0.07
     adaptations
    -0.07
     કાર
    -0.07
     Tac
    -0.07
    .true
    -0.07
    مپ
    -0.07
    .Then
    -0.07
     hely
    -0.07
    POSITIVE LOGITS
     FY
    0.08
    Fiscal
    0.08
    udal
    0.08
     quienes
    0.07
    ONTO
    0.07
    pret
    0.07
     sunn
    0.07
    JUST
    0.07
    894
    0.07
    violent
    0.07
    Activations Density 0.000%

    No Known Activations