© 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. 78425
    Prev
    Next
    INDEX
    Explanations

    Mathematical operations with symbols

    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
    èt
    -0.08
    icity
    -0.08
    ặn
    -0.08
    atic
    -0.07
    ettava
    -0.07
     Villar
    -0.07
    etter
    -0.07
    ит
    -0.07
     vital
    -0.07
    竟
    -0.07
    POSITIVE LOGITS
     económica
    0.08
     Raymond
    0.08
     baf
    0.08
     Experience
    0.08
    یل
    0.08
     والع
    0.08
     الخبر
    0.07
     香港
    0.07
     Taur
    0.07
     invocation
    0.07
    Activations Density 0.008%

    No Known Activations