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. 75980
    Prev
    Next
    INDEX
    Explanations

    iu

    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
    ITS
    -0.09
    Changing
    -0.08
    ्नु
    -0.08
     здійс
    -0.08
     дорого
    -0.08
    jų
    -0.08
    chst
    -0.08
    berichte
    -0.08
     Changing
    -0.08
    Infos
    -0.08
    POSITIVE LOGITS
     sense
    0.09
     ethics
    0.09
     humor
    0.09
    使命
    0.09
     morals
    0.09
     Sense
    0.08
    iliki
    0.08
     upright
    0.08
     юм
    0.08
     conscience
    0.08
    Activations Density 0.021%

    No Known Activations