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. 23-RESID-POST-AA
    6. 98260
    Prev
    Next
    INDEX
    Explanations

    denim/jeans clothing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    友情
    -0.09
     pants
    -0.09
    ukas
    -0.09
     polygons
    -0.08
    oks
    -0.08
     lunches
    -0.08
     Tmin
    -0.08
     半
    -0.08
     sandwiches
    -0.08
    	Vector
    -0.08
    POSITIVE LOGITS
     royal
    0.13
     mom
    0.09
     wife's
    0.08
     Dist
    0.08
     classic
    0.08
     raw
    0.08
    优秀
    0.08
    FFD
    0.07
     washed
    0.07
     high
    0.07
    Activations Density 0.005%

    No Known Activations