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. 98063
    Prev
    Next
    INDEX
    Explanations

    proverbs and sayings

    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
    รายละเอียด
    -0.08
     specifications
    -0.08
     extrusion
    -0.08
    参数
    -0.07
     parameters
    -0.07
     مشخص
    -0.07
     فایل
    -0.07
     details
    -0.07
     déta
    -0.07
    	parameters
    -0.07
    POSITIVE LOGITS
     proverb
    0.32
     sayings
    0.29
     whakata
    0.28
     Proverbs
    0.27
     કહેવ
    0.24
     поговор
    0.23
     saying
    0.23
     quote
    0.22
     motto
    0.22
     proverbial
    0.22
    Activations Density 0.088%

    No Known Activations