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. 59098
    Prev
    Next
    INDEX
    Explanations

    site

    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
     tricks
    -0.08
    Subscriber
    -0.08
     Samstag
    -0.07
     predecessor
    -0.07
     geheel
    -0.07
    ابقة
    -0.07
     distractions
    -0.07
    structor
    -0.07
    前
    -0.07
    inkgo
    -0.07
    POSITIVE LOGITS
     placements
    0.09
     Placement
    0.08
     wọn
    0.08
    �
    0.08
     afect
    0.08
     afectados
    0.08
     Deployment
    0.07
     الأماكن
    0.07
     ju
    0.07
    mui
    0.07
    Activations Density 0.006%

    No Known Activations