© 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. 71433
    Prev
    Next
    INDEX
    Explanations

    lib

    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
     leveraging
    -0.08
     주세요
    -0.08
    ，可以
    -0.07
     fazê
    -0.07
     Lanz
    -0.07
     темат
    -0.07
     demonstrated
    -0.07
     adhering
    -0.07
    Doing
    -0.07
     Tari
    -0.07
    POSITIVE LOGITS
     কারণে
    0.09
     métallique
    0.09
     menyebabkan
    0.09
    }(
    0.08
     GOP
    0.08
    342
    0.08
    _gpu
    0.08
    导致
    0.08
     tyr
    0.08
    prd
    0.08
    Activations Density 0.009%

    No Known Activations