© 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. 11-RESID-POST-AA
    11. 94984
    Prev
    Next
    INDEX
    Explanations

    parameter descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Celebr
    -0.09
     celebrating
    -0.09
     celebr
    -0.08
    Southern
    -0.08
    proof
    -0.08
     Southern
    -0.08
     admi
    -0.08
     infectious
    -0.08
    strategy
    -0.08
    ongo
    -0.08
    POSITIVE LOGITS
    字段
    0.12
     옵션
    0.11
     Deprecated
    0.11
     deprecated
    0.11
     کاربرد
    0.10
    参数
    0.10
     metavar
    0.10
     интерф
    0.10
    Deprecated
    0.10
    接口
    0.10
    Activations Density 0.056%

    No Known Activations