© 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. 48647
    Prev
    Next
    INDEX
    Explanations

    大

    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
     Linien
    -0.08
     दस
    -0.08
    .builder
    -0.08
     результат
    -0.08
    規
    -0.08
    响应
    -0.08
     लाइन
    -0.07
     attendre
    -0.07
    /read
    -0.07
    预计
    -0.07
    POSITIVE LOGITS
    大的
    0.11
    哥哥
    0.10
    盒彩
    0.10
    號
    0.10
    号
    0.10
    胃
    0.09
    红鹰
    0.09
    叔
    0.09
     guts
    0.08
    嫂
    0.08
    Activations Density 0.005%

    No Known Activations