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. 9051
    Prev
    Next
    INDEX
    Explanations

    graph chromatic number

    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
    анов
    -0.08
     آمده
    -0.08
     Governments
    -0.08
    .flush
    -0.08
     прошло
    -0.07
     RAID
    -0.07
    raan
    -0.07
     tier
    -0.07
     governo
    -0.07
     anúncio
    -0.07
    POSITIVE LOGITS
    Inet
    0.08
    Subdivision
    0.08
    Activate
    0.08
    chrom
    0.08
     squared
    0.08
    是多少
    0.08
    -half
    0.08
    Activ
    0.07
    猜
    0.07
     要
    0.07
    Activations Density 0.002%

    No Known Activations