© 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. 18252
    Prev
    Next
    INDEX
    Explanations

    File names

    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
    Not in Any Lists

    No Comments

    Negative Logits
     drainage
    -0.08
     transport
    -0.08
     runoff
    -0.08
     ડ્ર
    -0.08
     Dump
    -0.08
     descarga
    -0.08
     descarg
    -0.08
     herunterladen
    -0.08
    smtp
    -0.07
     دانلود
    -0.07
    POSITIVE LOGITS
     files
    0.15
     ファ
    0.14
     archivos
    0.13
    ファ
    0.13
     fichiers
    0.13
    .File
    0.13
     파일
    0.13
     arquivos
    0.13
     文件
    0.13
     الملفات
    0.13
    Activations Density 0.020%

    No Known Activations