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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96187
    Prev
    Next
    INDEX
    Explanations

    say SQL keywords

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trang
    -0.09
    сен
    -0.08
    ਾਇ
    -0.08
     carga
    -0.08
     >(
    -0.08
     Hồ
    -0.08
     Kuk
    -0.07
    ంక
    -0.07
     cargar
    -0.07
     carg
    -0.07
    POSITIVE LOGITS
    DO
    0.13
    _DO
    0.12
    \d
    0.11
    do
    0.10
    COMMENT
    0.10
     DO
    0.10
    \x
    0.09
    \
    0.09
     \
    0.09
    .Do
    0.09
    Activations Density 0.001%

    No Known Activations