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. 15-RESID-POST-AA
    6. 18726
    Prev
    Next
    INDEX
    Explanations

    language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :↵
    -0.09
    :↵↵
    -0.08
     lista
    -0.07
     supra
    -0.07
     atau
    -0.07
     perioada
    -0.07
     সপ্ত
    -0.07
     lub
    -0.07
    ↵   ↵
    -0.07
     ويمكن
    -0.07
    POSITIVE LOGITS
    urgent
    0.09
    ज्ञानिक
    0.09
    наком
    0.08
     ચલ
    0.08
     ಚಾಲ
    0.08
     погод
    0.08
     aparent
    0.08
    interop
    0.08
     насыщ
    0.08
     դեմ
    0.08
    Activations Density 0.011%

    No Known Activations