© 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. 17928
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
    Into
    -0.09
    uptools
    -0.08
    Shanghai
    -0.08
    Calibri
    -0.08
    Invoices
    -0.08
     viven
    -0.08
     बेला
    -0.08
    Strateg
    -0.08
    informatie
    -0.08
    Alibaba
    -0.08
    POSITIVE LOGITS
     ihany
    0.08
     nogle
    0.08
     previously
    0.08
     beberapa
    0.07
     anteriormente
    0.07
     code
    0.07
     similarly
    0.07
     várias
    0.07
     Alternatively
    0.07
     równie
    0.07
    Activations Density 0.000%

    No Known Activations