© 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. 19-RESID-POST-AA
    11. 18114
    Prev
    Next
    INDEX
    Explanations

    trigonometric identities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     perhaps
    -0.09
     probably
    -0.07
    with
    -0.07
    ickname
    -0.07
     likely
    -0.07
     with
    -0.07
     discuss
    -0.07
    _CAP
    -0.07
     schönsten
    -0.07
    ,
    -0.07
    POSITIVE LOGITS
     podob
    0.09
     similaire
    0.09
     sogenannte
    0.08
    лері
    0.08
    Lorsque
    0.08
     analogous
    0.08
     vaz
    0.08
    Бұл
    0.08
     બંને
    0.08
    Same
    0.08
    Activations Density 0.019%

    No Known Activations