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. 15-RESID-POST-AA
    6. 19169
    Prev
    Next
    INDEX
    Explanations

    counting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محور
    -0.08
     آرام
    -0.07
     تاريخ
    -0.07
    .jwt
    -0.07
     heil
    -0.07
     جذ
    -0.07
     serene
    -0.07
     زيارة
    -0.07
     soothing
    -0.07
     السيارة
    -0.07
    POSITIVE LOGITS
     counts
    0.11
    	count
    0.10
     count
    0.10
     계산
    0.10
     zählt
    0.09
     counted
    0.09
     zählen
    0.09
    是多少
    0.09
    count
    0.09
     मात्रा
    0.09
    Activations Density 0.043%

    No Known Activations