© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65510
    Prev
    Next
    INDEX
    Explanations

    math

    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
     pè
    -0.08
    hopefully
    -0.08
    kum
    -0.08
    的大
    -0.08
    огод
    -0.07
    étation
    -0.07
    헤
    -0.07
     pedig
    -0.07
     honra
    -0.07
     teljes
    -0.07
    POSITIVE LOGITS
     ln
    0.08
     singled
    0.07
    asan
    0.07
     trendy
    0.07
     Del
    0.07
     �
    0.07
     ટે
    0.07
    lol
    0.07
    /Documents
    0.07
    gh
    0.07
    Activations Density 0.012%

    No Known Activations