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. 58924
    Prev
    Next
    INDEX
    Explanations

    Islamic/Arabic context

    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
     locally
    -0.08
     pixels
    -0.08
     globally
    -0.08
     गर्म
    -0.07
    agt
    -0.07
    anne
    -0.07
     plated
    -0.07
     grammat
    -0.07
    agar
    -0.07
    ficiency
    -0.07
    POSITIVE LOGITS
     считать
    0.10
     حدیث
    0.09
     relatos
    0.08
     ṣee
    0.08
     relato
    0.08
    헌
    0.08
     provenance
    0.08
    .Linked
    0.08
     trajet
    0.08
     narrated
    0.08
    Activations Density 0.007%

    No Known Activations