© 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. 18082
    Prev
    Next
    INDEX
    Explanations

    999

    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
     सहायता
    -0.09
     on
    -0.09
     અંગે
    -0.08
     the
    -0.08
     both
    -0.08
     ધ્યાન
    -0.08
    援
    -0.08
    ，
    -0.08
     на
    -0.08
     મદદ
    -0.08
    POSITIVE LOGITS
    ffffffff
    0.13
    999
    0.12
    arently
    0.12
    llllllll
    0.11
    -",
    0.11
     میلیون
    0.11
    ahanol
    0.11
     veldig
    0.11
    aanng
    0.11
    bbbb
    0.11
    Activations Density 0.005%

    No Known Activations