© 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. 15-RESID-POST-AA
    11. 16688
    Prev
    Next
    INDEX
    Explanations

    related to math equations

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一定
    -0.08
    300
    -0.07
    શે
    -0.07
    stein
    -0.07
    043
    -0.07
    elia
    -0.07
    422
    -0.07
    383
    -0.07
    zan
    -0.07
     த
    -0.07
    POSITIVE LOGITS
     yaitu
    0.19
     yakni
    0.19
     یعنی
    0.14
     यानी
    0.14
     czyli
    0.13
     yani
    0.12
     namely
    0.11
     (=
    0.11
    자인
    0.11
    ，即
    0.10
    Activations Density 0.080%

    No Known Activations