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. 53981
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    hydrates
    -0.07
    פור
    -0.07
    Interrupt
    -0.07
    CONS
    -0.07
     shutter
    -0.07
    (config
    -0.07
     learned
    -0.07
    vind
    -0.07
    hydrate
    -0.07
     seren
    -0.07
    POSITIVE LOGITS
     gewährleisten
    0.09
     Trong
    0.08
     جہاں
    0.08
     Ft
    0.08
     excellent
    0.08
    _para
    0.08
     시간이
    0.08
     posiada
    0.08
    逸
    0.08
     qualitat
    0.08
    Activations Density 0.017%

    No Known Activations