© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 17901
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     various
    -0.11
     for
    -0.11
     and
    -0.11
     =
    -0.10
     Außerdem
    -0.10
     Zudem
    -0.10
     both
    -0.10
     તથા
    -0.09
     all
    -0.09
     zudem
    -0.09
    POSITIVE LOGITS
    Actually
    0.19
    However
    0.18
     Actually
    0.18
     BUT
    0.18
    BUT
    0.18
    Oops
    0.18
    actually
    0.17
    ولكن
    0.17
     However
    0.17
     Jednak
    0.17
    Activations Density 0.147%

    No Known Activations