Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30768
    Prev
    Next
    INDEX
    Explanations

    union of sets

    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
     लंबे
    -0.10
     بلند
    -0.09
    ethylene
    -0.09
     tranqu
    -0.08
    inguished
    -0.08
     गंभीर
    -0.08
    jections
    -0.08
     वजन
    -0.08
    털
    -0.07
     équipé
    -0.07
    POSITIVE LOGITS
    成立
    0.08
     ás
    0.08
     estat
    0.08
    {}↵↵
    0.07
     Kav
    0.07
    组合
    0.07
    结果
    0.07
     intre
    0.07
     terhadap
    0.07
    之后
    0.07
    Activations Density 0.019%

    No Known Activations