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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97313
    Prev
    Next
    INDEX
    Explanations

    say "monot" words

    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
     Badge
    -0.10
     Rebecca
    -0.09
     Chelsea
    -0.09
     Bad
    -0.09
     Wix
    -0.09
     Wars
    -0.09
     bbw
    -0.09
     damages
    -0.09
     Leia
    -0.09
     Perspective
    -0.09
    POSITIVE LOGITS
     monot
    0.26
     monoton
    0.22
     monopol
    0.19
     monet
    0.19
    Мон
    0.19
    _mon
    0.18
     мон
    0.18
    .mon
    0.18
     مون
    0.18
     მონ
    0.18
    Activations Density 0.023%

    No Known Activations