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. 78266
    Prev
    Next
    INDEX
    Explanations

    regions

    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
     ausgesprochen
    -0.08
    债
    -0.08
     ligação
    -0.08
    chedule
    -0.08
    ousal
    -0.08
     indebted
    -0.08
     amizade
    -0.08
     irmãos
    -0.07
     appeal
    -0.07
    言
    -0.07
    POSITIVE LOGITS
    Region
    0.14
     region
    0.13
     regiones
    0.13
     منطقة
    0.12
     cropped
    0.12
     regions
    0.12
     области
    0.12
     ప్రాంత
    0.12
    _REGION
    0.12
     область
    0.12
    Activations Density 0.012%

    No Known Activations