© 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. 19-RESID-POST-AA
    11. 18175
    Prev
    Next
    INDEX
    Explanations

    say "Return" or "Determine"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ၃
    -0.09
    Ổ
    -0.09
     servido
    -0.08
     หา
    -0.08
    ५०
    -0.08
     autoridade
    -0.08
    ൂടെ
    -0.08
     dermed
    -0.08
     mestu
    -0.08
    traffic
    -0.08
    POSITIVE LOGITS
     pant
    0.08
    .↵
    0.08
    >B
    0.08
    判断
    0.08
    _return
    0.08
     эта
    0.08
    _Id
    0.08
    _utils
    0.07
    ,B
    0.07
    _id
    0.07
    Activations Density 0.000%

    No Known Activations