© 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. 75663
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    .l
    -0.08
     misc
    -0.08
    rides
    -0.08
     fumar
    -0.08
     Ache
    -0.08
    op
    -0.08
     ச
    -0.07
     hunter
    -0.07
     Citizen
    -0.07
     crack
    -0.07
    POSITIVE LOGITS
    ॅ
    0.08
    ্
    0.07
     Escort
    0.07
    Fen
    0.07
     ```↵
    0.07
    आप
    0.07
    ​↵
    0.07
    हा
    0.07
    ウ
    0.07
    央
    0.07
    Activations Density 0.079%

    No Known Activations