© 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. 11-RESID-POST-AA
    11. 30210
    Prev
    Next
    INDEX
    Explanations

    tired

    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
     Sizes
    -0.08
     размеры
    -0.08
     Schwartz
    -0.08
    !--
    -0.07
     Esc
    -0.07
    grö
    -0.07
     Fire
    -0.07
     Aman
    -0.07
     Chambers
    -0.07
     Languages
    -0.07
    POSITIVE LOGITS
    been
    0.09
     battered
    0.08
     hum
    0.08
    暇
    0.08
     hardworking
    0.08
    oton
    0.08
     tired
    0.08
     hålla
    0.08
     boredom
    0.08
    Enough
    0.07
    Activations Density 0.009%

    No Known Activations