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. 103021
    Prev
    Next
    INDEX
    Explanations

    record/log

    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
     Muse
    -0.08
     MSNBC
    -0.08
    стве
    -0.08
     fashionable
    -0.08
     immoral
    -0.08
    clusters
    -0.07
    mig
    -0.07
    حمة
    -0.07
     resolução
    -0.07
     comedic
    -0.07
    POSITIVE LOGITS
    记录
    0.11
     기록
    0.10
     temperature
    0.10
     datas
    0.10
    .record
    0.10
    /report
    0.10
    ournal
    0.09
    .Record
    0.09
    纪录
    0.09
     temperatures
    0.09
    Activations Density 0.021%

    No Known Activations