© 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. 71474
    Prev
    Next
    INDEX
    Explanations

    ..

    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
    Not in Any Lists

    No Comments

    Negative Logits
    _alive
    -0.08
     rand
    -0.08
     cust
    -0.08
     fucking
    -0.08
     pik
    -0.07
    _demo
    -0.07
     tup
    -0.07
     pest
    -0.07
     oled
    -0.07
    -al
    -0.07
    POSITIVE LOGITS
     hmm
    0.08
     Stevens
    0.07
    ikon
    0.07
    なので
    0.07
    تر
    0.07
    Poss
    0.07
    ein
    0.07
    anner
    0.07
     Gazette
    0.07
    '↵↵↵
    0.07
    Activations Density 0.096%

    No Known Activations