© 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. 11-RESID-POST-AA
    11. 109811
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     அவ
    -0.09
     Hay
    -0.09
     പ്രത
    -0.08
     Ice
    -0.08
     Australia's
    -0.08
     Canada's
    -0.08
     вд
    -0.08
     ice
    -0.07
     ಅವ
    -0.07
     అవ
    -0.07
    POSITIVE LOGITS
    _BEGIN
    0.08
     fahr
    0.08
    649
    0.07
    -bearing
    0.07
    crm
    0.07
    _holder
    0.07
     utilisateur
    0.07
    Five
    0.07
    aggia
    0.07
    ಕ್ಕಾಗಿ
    0.07
    Activations Density 0.090%

    No Known Activations