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. 90208
    Prev
    Next
    INDEX
    Explanations

    rubrics

    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
    .cache
    -0.08
    .png
    -0.08
     Leisure
    -0.07
    骗局
    -0.07
    куда
    -0.07
    -temperature
    -0.07
    -ui
    -0.07
     Freizeit
    -0.07
    -screen
    -0.07
    Ther
    -0.07
    POSITIVE LOGITS
     excellence
    0.11
     qualifications
    0.11
     mastery
    0.11
     proficiency
    0.10
     स्तर
    0.10
    ระดับ
    0.10
     qualitat
    0.10
    _grade
    0.10
     excelência
    0.10
     qualific
    0.10
    Activations Density 0.009%

    No Known Activations