© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97484
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
    字段
    -0.09
     Energ
    -0.09
    提高
    -0.08
    类别
    -0.08
     entusiasmo
    -0.08
     Aerospace
    -0.08
    że
    -0.08
     האט
    -0.08
     rythme
    -0.07
    长度
    -0.07
    POSITIVE LOGITS
     京城
    0.16
     人妻
    0.16
    爆乳
    0.15
     赌
    0.15
    人妻
    0.15
    三级片
    0.15
    尼姑
    0.15
    反水
    0.15
    偷拍
    0.15
    凰
    0.15
    Activations Density 0.024%

    No Known Activations