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. 88274
    Prev
    Next
    INDEX
    Explanations

    carbon

    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
    公安
    -0.08
     Mir
    -0.08
    Ken
    -0.08
     cym
    -0.08
    -0.08
     MIG
    -0.07
     Mend
    -0.07
     Lug
    -0.07
    loxacin
    -0.07
     nice
    -0.07
    POSITIVE LOGITS
     dioxide
    0.09
    elsius
    0.08
    马
    0.08
    饮
    0.08
    ifer
    0.08
    گذاری
    0.07
     прин
    0.07
    987
    0.07
    -coded
    0.07
     swirling
    0.07
    Activations Density 0.010%

    No Known Activations