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. 78581
    Prev
    Next
    INDEX
    Explanations

    yoga

    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
    	r
    -0.08
    突
    -0.08
    	z
    -0.08
     polym
    -0.07
    との差
    -0.07
    chunk
    -0.07
    ooled
    -0.07
    _chunk
    -0.07
     ogl
    -0.07
     توسط
    -0.07
    POSITIVE LOGITS
     yoga
    0.11
     Yoga
    0.11
     mindfulness
    0.10
    Yoga
    0.09
     भग
    0.09
     практике
    0.08
     kar
    0.08
     joog
    0.08
     Mari
    0.08
     Meditation
    0.08
    Activations Density 0.006%

    No Known Activations