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

    Neuronpedia

    APICircuit 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. 166
    Prev
    Next
    INDEX
    Explanations

    Technical analysis in multiple languages

    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
    aphne
    -0.09
     Chaque
    -0.08
    uelt
    -0.08
    Performed
    -0.08
     또한
    -0.08
     personally
    -0.08
    ult
    -0.08
     Concept
    -0.08
     Positioned
    -0.08
    ualquier
    -0.08
    POSITIVE LOGITS
     puhul
    0.14
     analysis
    0.11
     optimization
    0.09
    analysis
    0.09
     resilience
    0.09
     સુધ
    0.09
     stability
    0.09
     تحسين
    0.09
     kohd
    0.09
     debugging
    0.09
    Activations Density 0.108%

    No Known Activations