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. 74833
    Prev
    Next
    INDEX
    Explanations

    a/the

    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
    전에
    -0.08
    전
    -0.08
    세
    -0.08
     Locations
    -0.08
    사이트
    -0.08
    회사
    -0.08
     Interpreter
    -0.07
     interpretar
    -0.07
     judge
    -0.07
     juiz
    -0.07
    POSITIVE LOGITS
     მი
    0.10
     ელ
    0.09
     მოთ
    0.09
     წარმოდ
    0.09
     эв
    0.09
     պատ
    0.09
     offic
    0.08
    éasáin
    0.08
     मु
    0.08
     მზად
    0.08
    Activations Density 0.008%

    No Known Activations