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. 112104
    Prev
    Next
    INDEX
    Explanations

    cycle

    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
     Unix
    -0.08
     ау
    -0.08
     freie
    -0.08
     невер
    -0.08
    	file
    -0.07
     ohnehin
    -0.07
     mú
    -0.07
     Eliot
    -0.07
     file
    -0.07
     сир
    -0.07
    POSITIVE LOGITS
     durability
    0.11
     endurance
    0.10
     longevity
    0.09
     الأداء
    0.09
     Tested
    0.09
     duurzaamheid
    0.09
     عملکرد
    0.09
    formance
    0.08
     reproduc
    0.08
     duurzaam
    0.08
    Activations Density 0.006%

    No Known Activations