© 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. 19-RESID-POST-AA
    11. 103064
    Prev
    Next
    INDEX
    Explanations

    Korean descriptions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     zult
    -0.10
     kunt
    -0.09
    りまして
    -0.09
     değildir
    -0.09
    用了
    -0.09
    看的
    -0.09
    ですよ
    -0.09
     olmayan
    -0.08
     서비스를
    -0.08
     peate
    -0.08
    POSITIVE LOGITS
     있음
    0.21
    됨
    0.16
    ۔↵
    0.15
    ؛
    0.14
    ।↵
    0.14
    ।
    0.14
     없음
    0.13
    ۔
    0.13
    ။↵
    0.13
    ۔↵↵
    0.13
    Activations Density 0.022%

    No Known Activations