© 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. 17977
    Prev
    Next
    INDEX
    Explanations

    Source attribution

    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
     usual
    -0.08
     wont
    -0.08
     uses
    -0.08
     famosas
    -0.07
     choice
    -0.07
     own
    -0.07
     egne
    -0.07
     meme
    -0.07
    ixture
    -0.07
    >).
    -0.07
    POSITIVE LOGITS
    นัน
    0.08
    дарды
    0.07
    elja
    0.07
     Þá
    0.07
    -J
    0.07
    -ज
    0.07
    ځ
    0.07
    _dc
    0.07
    ృద్ధ
    0.07
    -Air
    0.07
    Activations Density 0.005%

    No Known Activations