© 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. 49001
    Prev
    Next
    INDEX
    Explanations

    例

    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
    ്ഘ
    -0.09
    (end
    -0.09
    ացած
    -0.08
    խ
    -0.08
    ്യത
    -0.08
    ,end
    -0.08
    ómica
    -0.08
    ൃത
    -0.08
    ിയുടെ
    -0.08
    ിദ
    -0.08
    POSITIVE LOGITS
    子
    0.23
    子的
    0.18
     子
    0.16
    证
    0.14
    句
    0.12
    外
    0.12
    제를
    0.11
    시
    0.10
    え
    0.10
    程
    0.10
    Activations Density 0.002%

    No Known Activations