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. 75116
    Prev
    Next
    INDEX
    Explanations

    encryption code

    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
     temptation
    -0.09
    (results
    -0.08
     canapé
    -0.08
    Resultados
    -0.08
    지를
    -0.08
     Fell
    -0.08
     Feeding
    -0.08
    誘惑
    -0.07
    Behaviour
    -0.07
     sofá
    -0.07
    POSITIVE LOGITS
     assur
    0.08
    ਜ਼
    0.07
     byl
    0.07
     lucky
    0.07
     સંપર્ક
    0.07
    ज़
    0.07
     assurer
    0.07
     idan
    0.07
     pancreas
    0.07
    iaz
    0.07
    Activations Density 0.007%

    No Known Activations