© 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. 109775
    Prev
    Next
    INDEX
    Explanations

    encryption and keys

    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
    Woman
    -0.09
     raggi
    -0.09
     Woman
    -0.09
     cheddar
    -0.09
     Fiverr
    -0.08
     arred
    -0.08
     tobacco
    -0.08
     Lemon
    -0.08
     женщины
    -0.08
    ček
    -0.08
    POSITIVE LOGITS
     secrets
    0.09
     securely
    0.09
     गो
    0.09
    _SECRET
    0.09
    钥
    0.08
    (secret
    0.08
     distributed
    0.08
    密
    0.08
     वित
    0.08
    秘密
    0.08
    Activations Density 0.009%

    No Known Activations