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. 15-RESID-POST-AA
    6. 19079
    Prev
    Next
    INDEX
    Explanations

    math problems

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ур
    -0.10
     прогноз
    -0.09
     aim
    -0.09
     أهداف
    -0.09
     مر
    -0.09
     centered
    -0.09
    Centered
    -0.09
     прим
    -0.09
     Цент
    -0.08
     порт
    -0.08
    POSITIVE LOGITS
    与
    0.08
    -business
    0.07
    于是
    0.07
    和值
    0.07
    	db
    0.07
     publier
    0.07
     与
    0.07
    仅
    0.07
     Dunk
    0.07
    和
    0.07
    Activations Density 0.007%

    No Known Activations