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. 44083
    Prev
    Next
    INDEX
    Explanations

    .emit

    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
     repress
    -0.07
    (orig
    -0.07
    Undo
    -0.07
     Baba
    -0.07
    (nt
    -0.07
     paradox
    -0.07
     зраб
    -0.07
     Recycling
    -0.07
    Routine
    -0.07
     ಪಡೆದ
    -0.07
    POSITIVE LOGITS
     COMMENTS
    0.09
    滨
    0.08
     lenn
    0.08
     analiza
    0.08
     TERMS
    0.08
    aville
    0.08
    ician
    0.08
     hundreds
    0.08
    十大
    0.08
     coastal
    0.08
    Activations Density 0.000%

    No Known Activations