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. 44092
    Prev
    Next
    INDEX
    Explanations

    #

    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
     crack
    -0.09
     fund
    -0.09
    .Dictionary
    -0.08
    )</
    -0.08
    /List
    -0.08
    perk
    -0.08
    <Route
    -0.08
    wicklung
    -0.08
    <Array
    -0.08
    empre
    -0.08
    POSITIVE LOGITS
                                                     
    0.07
    DEFAULT
    0.07
    qq
    0.07
                                                                 
    0.07
     bwa
    0.07
     BC
    0.07
    -dev
    0.07
                                                      
    0.07
    ba
    0.07
    Src
    0.06
    Activations Density 0.002%

    No Known Activations