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. 49257
    Prev
    Next
    INDEX
    Explanations

    thoughts

    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
     এলাক
    -0.08
     stewardship
    -0.08
     neph
    -0.07
     Upr
    -0.07
     PNG
    -0.07
     Panch
    -0.07
     Sunset
    -0.07
    সহ
    -0.07
     variantes
    -0.07
     chỉnh
    -0.07
    POSITIVE LOGITS
     intentions
    0.13
    Intent
    0.11
     Intent
    0.11
     intenção
    0.10
     workings
    0.10
     intención
    0.10
    	Intent
    0.10
     intention
    0.10
     pensamentos
    0.09
     inten
    0.09
    Activations Density 0.043%

    No Known Activations