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. 12151
    Prev
    Next
    INDEX
    Explanations

    lettuce

    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
     manifestation
    -0.08
    Manifest
    -0.08
     இர
    -0.08
     conoscere
    -0.08
    ignment
    -0.07
     சக
    -0.07
     escal
    -0.07
    ponent
    -0.07
     ga
    -0.07
    aban
    -0.07
    POSITIVE LOGITS
     Dorothy
    0.08
     founders
    0.08
     FMC
    0.08
     Samp
    0.07
     Timothy
    0.07
     Tropical
    0.07
     Mille
    0.07
    阅
    0.07
     fresca
    0.07
     tortillas
    0.07
    Activations Density 0.002%

    No Known Activations