© 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. 71442
    Prev
    Next
    INDEX
    Explanations

    inequalities

    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
    SSA
    -0.09
     fjöl
    -0.08
     SSA
    -0.08
     }↵↵↵↵
    -0.08
     Praia
    -0.07
     sinun
    -0.07
    ogaeth
    -0.07
     aasta
    -0.07
     pili
    -0.07
    ssa
    -0.07
    POSITIVE LOGITS
    宽
    0.08
    0.07
     Wit
    0.07
    .circle
    0.07
    _DROP
    0.07
     cuadr
    0.07
    Wise
    0.07
     genü
    0.07
     volum
    0.07
     usable
    0.07
    Activations Density 0.012%
    No Known Activations