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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 112949
    Prev
    Next
    INDEX
    Explanations

    single quote

    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
     సర
    -0.08
     waterfront
    -0.08
     Verg
    -0.08
    ాల్
    -0.08
     Memor
    -0.08
     Stimmen
    -0.08
     Singapore
    -0.08
     Tall
    -0.08
     voces
    -0.08
     Mais
    -0.08
    POSITIVE LOGITS
    cks
    0.08
    Br
    0.08
    sole
    0.08
    EOF
    0.08
    Exchange
    0.07
    으
    0.07
     overcame
    0.07
    tren
    0.07
    To
    0.07
     punched
    0.07
    Activations Density 0.000%

    No Known Activations