© 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. 19-RESID-POST-AA
    11. 102969
    Prev
    Next
    INDEX
    Explanations

    ."

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     易乐
    -0.13
     开元棋牌
    -0.13
    】【“】【
    -0.13
     奥门
    -0.13
    热久久精品
    -0.13
     正点
    -0.13
     түш
    -0.13
     东臣
    -0.12
    全天计划
    -0.12
    娱乐代理
    -0.12
    POSITIVE LOGITS
     be
    0.07
     Simulation
    0.07
     Testing
    0.07
    cac
    0.07
    s
    0.07
     Commander
    0.07
     Support
    0.06
    sis
    0.06
     DFS
    0.06
     Tests
    0.06
    Activations Density 0.239%

    No Known Activations