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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70427
    Prev
    Next
    INDEX
    Explanations

    adverbs for productivity

    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
     everybody
    -0.14
     spite
    -0.10
     everytime
    -0.10
     horribly
    -0.10
     anybody
    -0.10
    -able
    -0.10
     stuffs
    -0.10
     somebody
    -0.10
     Everybody
    -0.09
     monies
    -0.09
    POSITIVE LOGITS
     meticulously
    0.10
     captivating
    0.10
     showcases
    0.09
     primarily
    0.09
     showcasing
    0.08
     حول
    0.08
    ажно
    0.08
     intric
    0.08
     intricate
    0.08
      ↵
    0.08
    Activations Density 0.713%

    No Known Activations