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. 15-RESID-POST-AA
    6. 19683
    Prev
    Next
    INDEX
    Explanations

    stress

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     show's
    -0.08
     alfabet
    -0.08
     بأس
    -0.08
    ayout
    -0.08
     الرسمية
    -0.08
     breakfast
    -0.08
     Breakfast
    -0.08
     classy
    -0.08
     Fern
    -0.08
     versed
    -0.07
    POSITIVE LOGITS
     Belast
    0.15
     stress
    0.14
     нагруз
    0.14
     stresses
    0.14
     부담
    0.13
     belast
    0.13
     stressful
    0.13
     нагрузки
    0.13
    Stress
    0.13
     Stress
    0.12
    Activations Density 0.019%

    No Known Activations