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. 27497
    Prev
    Next
    INDEX
    Explanations

    odd numbers

    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
     dialect
    -0.09
     Calend
    -0.09
     работод
    -0.08
     الدع
    -0.08
     Comerc
    -0.08
     мировой
    -0.08
     узна
    -0.08
     رئیس
    -0.07
     travels
    -0.07
     бағыт
    -0.07
    POSITIVE LOGITS
    人数
    0.12
    -count
    0.10
     count
    0.09
     counted
    0.09
    .count
    0.09
    Counts
    0.09
    Count
    0.09
    -five
    0.09
    ,count
    0.09
    -four
    0.09
    Activations Density 0.040%

    No Known Activations