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. 49096
    Prev
    Next
    INDEX
    Explanations

    Units of time

    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
     fiercely
    -0.08
     vigorous
    -0.08
     sucking
    -0.08
     watering
    -0.07
     surg
    -0.07
     culin
    -0.07
     spirited
    -0.07
    MVC
    -0.07
     links
    -0.07
    watering
    -0.07
    POSITIVE LOGITS
     점
    0.08
     ARRAY
    0.08
    алып
    0.08
     श्रृ
    0.07
    127
    0.07
     Highway
    0.07
     paar
    0.07
     VIII
    0.07
    	trace
    0.07
     ответственности
    0.07
    Activations Density 0.021%

    No Known Activations