© 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. 18232
    Prev
    Next
    INDEX
    Explanations

    own

    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
     another
    -0.13
    other
    -0.12
    another
    -0.12
     Andere
    -0.12
     anderes
    -0.12
     andere
    -0.11
     otros
    -0.11
     otras
    -0.11
     otro
    -0.11
     Another
    -0.11
    POSITIVE LOGITS
     respective
    0.12
     жеке
    0.12
     уник
    0.12
     unique
    0.12
     unieke
    0.11
     personal
    0.10
     bijdrage
    0.10
     μονα
    0.09
     einzigartige
    0.09
     гэсэн
    0.09
    Activations Density 0.026%

    No Known Activations