© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21301
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ۽
    -0.10
     그리고
    -0.10
     and
    -0.09
     और
    -0.09
    -0.09
     ਅਤੇ
    -0.09
    ogical
    -0.09
    そして
    -0.09
     සහ
    -0.09
     zowel
    -0.09
    POSITIVE LOGITS
    maybe
    0.15
     maybe
    0.15
    TODO
    0.13
     commented
    0.12
     TODO
    0.11
    Maybe
    0.11
    debug
    0.11
    todo
    0.11
    if
    0.11
     possibly
    0.11
    Activations Density 0.009%
    No Known Activations