© 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. 18133
    Prev
    Next
    INDEX
    Explanations

    math and chemistry problems

    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
    Todas
    -0.10
    Debe
    -0.09
     dialogs
    -0.09
     kabeh
    -0.09
    Ahora
    -0.09
     সকলো
    -0.09
     debates
    -0.08
    Ora
    -0.08
     அனைத்து
    -0.08
     բոլոր
    -0.08
    POSITIVE LOGITS
     fame
    0.08
    ).↵↵
    0.07
    ferred
    0.07
     Leadership
    0.07
    ".↵↵
    0.07
    ),
    0.07
    oun
    0.07
    ॉप
    0.07
     fameux
    0.07
     "
    0.07
    Activations Density 0.000%

    No Known Activations