© 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. 18270
    Prev
    Next
    INDEX
    Explanations

    is

    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
     {↵/
    -0.08
    yyat
    -0.07
     superiores
    -0.07
    emes
    -0.07
    وعة
    -0.07
     enlaces
    -0.07
     വിവിധ
    -0.07
    .bs
    -0.07
    (){↵
    -0.07
     getters
    -0.07
    POSITIVE LOGITS
     among
    0.30
     included
    0.27
    among
    0.25
     Among
    0.25
     amongst
    0.25
     parmi
    0.24
    Among
    0.24
     blandt
    0.24
     među
    0.23
     Included
    0.23
    Activations Density 0.062%

    No Known Activations