© 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. 6084
    Prev
    Next
    INDEX
    Explanations

    生

    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
     fixes
    -0.08
    enação
    -0.08
     tarp
    -0.08
     wah
    -0.07
    enski
    -0.07
    afone
    -0.07
     ří
    -0.07
    nacht
    -0.07
     stomp
    -0.07
    wah
    -0.07
    POSITIVE LOGITS
    涯
    0.16
    殖
    0.14
    겼
    0.12
    物
    0.12
    姜
    0.12
    辰
    0.12
    ま
    0.11
    育
    0.10
    存
    0.10
    產
    0.10
    Activations Density 0.003%

    No Known Activations