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. 7-RESID-POST-AA
    6. 131027
    Prev
    Next
    INDEX
    Explanations

    deemed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seen
    -0.09
     monop
    -0.08
     Zen
    -0.07
    Compl
    -0.07
     misinformation
    -0.07
    inode
    -0.07
    dans
    -0.07
     gönd
    -0.07
     보내
    -0.07
    link
    -0.07
    POSITIVE LOGITS
    繁
    0.09
     unforgettable
    0.07
    腐
    0.07
     निर्�
    0.07
     iub
    0.07
    hyr
    0.07
    _runner
    0.07
    ppy
    0.07
    eg
    0.07
    epa
    0.07
    Activations Density 0.002%

    No Known Activations