Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44061
    Prev
    Next
    INDEX
    Explanations

    disability insurance

    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
     bik
    -0.08
     Bajo
    -0.08
     Komis
    -0.08
     Skate
    -0.08
    体系
    -0.08
    SSION
    -0.08
     skateboard
    -0.07
     indrindra
    -0.07
     Indo
    -0.07
     Parque
    -0.07
    POSITIVE LOGITS
     illness
    0.09
     rô
    0.09
    	selected
    0.08
     stiff
    0.08
     illnesses
    0.08
     смерти
    0.08
     disabilities
    0.08
     courage
    0.08
    income
    0.08
     bedside
    0.07
    Activations Density 0.006%

    No Known Activations