© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103109
    Prev
    Next
    INDEX
    Explanations

    disability and impairment

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     warms
    -0.10
     bullish
    -0.09
     warming
    -0.08
     temperatura
    -0.08
     quente
    -0.08
    ++)
    -0.08
     θερ
    -0.08
     الساخ
    -0.08
     горяч
    -0.08
     instantly
    -0.08
    POSITIVE LOGITS
     disability
    0.20
     impairment
    0.20
     impaired
    0.19
     debilitating
    0.19
     impair
    0.18
     disabilities
    0.18
     Disability
    0.17
     beein
    0.17
    生活
    0.16
     occupational
    0.16
    Activations Density 0.031%

    No Known Activations