Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 76178
    Prev
    Next
    INDEX
    Explanations

    recipes and meal suggestions

    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
    quite
    -0.08
     endure
    -0.07
    asons
    -0.07
    Things
    -0.07
    Autowired
    -0.07
     mili
    -0.07
     Huge
    -0.07
     Wiring
    -0.07
    >>()
    -0.07
    Touched
    -0.07
    POSITIVE LOGITS
     looming
    0.08
     તૈયાર
    0.08
     scrapy
    0.08
    rcode
    0.08
     પાલ
    0.08
    innu
    0.07
     newline
    0.07
     مني
    0.07
     അമേരിക്ക
    0.07
     isang
    0.07
    Activations Density 0.014%

    No Known Activations