Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54139
    Prev
    Next
    INDEX
    Explanations

    power consumption

    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
    =date
    -0.08
     droom
    -0.08
     tanggal
    -0.08
     date
    -0.08
    延期
    -0.08
     insightful
    -0.08
     emphasize
    -0.08
     enfat
    -0.08
     narrative
    -0.08
     monuments
    -0.08
    POSITIVE LOGITS
     watts
    0.11
     تشغيل
    0.10
    idle
    0.09
     الجهاز
    0.09
    _IDLE
    0.09
     idle
    0.09
     amps
    0.09
    Idle
    0.09
     нагрузки
    0.09
    Battery
    0.09
    Activations Density 0.011%

    No Known Activations