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. 19507
    Prev
    Next
    INDEX
    Explanations

    average

    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
    ერიო
    -0.09
     olul
    -0.08
    �
    -0.08
    ترات
    -0.08
     мона
    -0.08
    ారా
    -0.08
     siapa
    -0.08
    анты
    -0.08
    فال
    -0.08
    ください
    -0.08
    POSITIVE LOGITS
     promedio
    0.11
     average
    0.11
     moyen
    0.10
     durchschnitt
    0.10
     평균
    0.10
     moyenne
    0.10
     Durchschnitt
    0.10
     gemiddeld
    0.10
    average
    0.09
    平均
    0.09
    Activations Density 0.043%

    No Known Activations