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. 90042
    Prev
    Next
    INDEX
    Explanations

    food science and technology

    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
     ág
    -0.09
     fundraiser
    -0.09
     tuition
    -0.09
     chaise
    -0.08
    _REMOTE
    -0.08
    柴
    -0.08
    疯狂
    -0.08
     craigslist
    -0.08
     Paypal
    -0.08
    서울
    -0.08
    POSITIVE LOGITS
     shelf
    0.11
     preservatives
    0.10
     lactose
    0.09
     स्वाद
    0.09
     moisture
    0.09
     packaging
    0.09
     Shelf
    0.09
     whiten
    0.08
     aging
    0.08
     allergens
    0.08
    Activations Density 0.022%

    No Known Activations