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. 12234
    Prev
    Next
    INDEX
    Explanations

    geography, biomes, 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
    ancell
    -0.09
    -approved
    -0.09
     accountability
    -0.08
     Accountability
    -0.08
     privacy
    -0.08
     distractions
    -0.08
     escrow
    -0.08
    anjang
    -0.08
     distraction
    -0.08
     pulley
    -0.08
    POSITIVE LOGITS
     geographical
    0.10
     geographically
    0.10
     Classification
    0.10
     climatic
    0.10
    地域
    0.10
     Geographic
    0.10
     classification
    0.10
     Geography
    0.10
     Regional
    0.09
     classifications
    0.09
    Activations Density 0.011%

    No Known Activations