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. 75264
    Prev
    Next
    INDEX
    Explanations

    Lists or sets

    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
    -times
    -0.09
     aggressively
    -0.07
     magnet
    -0.07
     tekem
    -0.07
     unauthorized
    -0.07
     säh
    -0.07
     bounced
    -0.07
     మ్యాచ్
    -0.07
    Xe
    -0.07
    [end
    -0.07
    POSITIVE LOGITS
    三个
    0.12
     terdiri
    0.12
     pilares
    0.12
     ארבע
    0.11
     quatre
    0.11
     الأربع
    0.11
     четыре
    0.10
     cuatro
    0.10
    体系
    0.10
     pillars
    0.10
    Activations Density 0.102%

    No Known Activations