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. 12919
    Prev
    Next
    INDEX
    Explanations

    code and databases

    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
     support
    -0.07
    کس
    -0.07
    esco
    -0.07
     oficialmente
    -0.07
     يش
    -0.07
    Fld
    -0.07
     aim
    -0.07
     Oc
    -0.07
     atoa
    -0.07
     الجن
    -0.07
    POSITIVE LOGITS
    idus
    0.09
    Save
    0.08
     capitalist
    0.08
    Larry
    0.08
    保存
    0.08
     bouncing
    0.08
    !*
    0.08
     insensitive
    0.08
     siebie
    0.08
     capitalism
    0.08
    Activations Density 0.001%

    No Known Activations