© 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. 68304
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     Elemente
    -0.08
    lernen
    -0.08
     Salut
    -0.08
     احساس
    -0.08
     situated
    -0.08
     synt
    -0.08
     Wissenschaft
    -0.08
     Earth
    -0.08
     ped
    -0.07
    Salut
    -0.07
    POSITIVE LOGITS
    .baomidou
    0.16
    分页
    0.14
    业务
    0.14
     Alibaba
    0.13
     layui
    0.13
    omidou
    0.13
    Batis
    0.12
    batis
    0.12
    .mybatis
    0.11
    .mybatisplus
    0.11
    Activations Density 0.017%

    No Known Activations