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. 112172
    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
     upt
    -0.07
     pul
    -0.07
     Pul
    -0.07
    Pul
    -0.07
     sanctuary
    -0.07
     entram
    -0.07
     rehe
    -0.07
     Len
    -0.07
    /is
    -0.07
     energet
    -0.07
    POSITIVE LOGITS
    wpdb
    0.09
    GLOBALS
    0.09
     horn
    0.08
     aqu
    0.08
    עז
    0.08
    باب
    0.08
    HOME
    0.08
    #$
    0.07
    subst
    0.07
    FAIL
    0.07
    Activations Density 0.014%

    No Known Activations