Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 94968
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
    human
    -0.08
     inspiration
    -0.08
    hy
    -0.08
     Inspiration
    -0.07
     clearly
    -0.07
    ty
    -0.07
    spaces
    -0.07
     Bein
    -0.07
    -Ber
    -0.07
    류
    -0.07
    POSITIVE LOGITS
     impost
    0.11
     compelled
    0.09
    ಿಯಿಂದ
    0.09
     fuga
    0.08
     oce
    0.08
     anul
    0.08
     ограничения
    0.08
     sopr
    0.08
    Lat
    0.08
     urges
    0.08
    Activations Density 0.001%

    No Known Activations