© 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. 109991
    Prev
    Next
    INDEX
    Explanations

    ly

    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
    bg
    -0.08
     elas
    -0.08
    =array
    -0.08
    Bart
    -0.08
     Bakers
    -0.08
     erl
    -0.08
    nek
    -0.08
    mdl
    -0.07
     turmoil
    -0.07
    loch
    -0.07
    POSITIVE LOGITS
     рекоменду
    0.09
     outweigh
    0.09
     recommend
    0.09
    认为
    0.09
     рекомендуется
    0.08
     encouraged
    0.08
     urge
    0.08
     believe
    0.08
     urged
    0.08
     recomand
    0.08
    Activations Density 0.019%

    No Known Activations