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. 15-RESID-POST-AA
    6. 19474
    Prev
    Next
    INDEX
    Explanations

    f

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ทร
    -0.09
     prazo
    -0.08
     комплект
    -0.08
     SOC
    -0.08
    inske
    -0.08
    ρκ
    -0.07
     nacionais
    -0.07
    ครง
    -0.07
     коя
    -0.07
    tid
    -0.07
    POSITIVE LOGITS
    值
    0.13
     values
    0.11
    -values
    0.11
    values
    0.10
     değer
    0.10
    値
    0.10
    값
    0.10
     значения
    0.10
     값
    0.10
    value
    0.10
    Activations Density 0.045%

    No Known Activations