© 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. 96750
    Prev
    Next
    INDEX
    Explanations

    养

    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
     borrowing
    -0.08
    (bounds
    -0.08
     Emmy
    -0.07
     embroidery
    -0.07
     奇
    -0.07
     Mär
    -0.07
    artig
    -0.07
    ട്ട്
    -0.07
     Talk
    -0.07
    ạn
    -0.07
    POSITIVE LOGITS
    殖
    0.14
    护
    0.12
    生
    0.11
    成
    0.11
    分
    0.10
    護
    0.10
    份
    0.09
    尊
    0.09
    蜂
    0.09
    分快
    0.09
    Activations Density 0.002%

    No Known Activations