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. 102871
    Prev
    Next
    INDEX
    Explanations

    stress

    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
     पकड़
    -0.09
     Subscription
    -0.08
     Captain
    -0.08
     luas
    -0.08
    همية
    -0.07
     Download
    -0.07
     Craigslist
    -0.07
     dresser
    -0.07
     Reagan
    -0.07
     διαθέ
    -0.07
    POSITIVE LOGITS
     stress
    0.12
     stressful
    0.11
     стресс
    0.11
    Stress
    0.11
     abi
    0.10
     stresses
    0.10
     estrés
    0.10
     напряж
    0.10
    stress
    0.10
     Stress
    0.09
    Activations Density 0.013%

    No Known Activations