© 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. 95194
    Prev
    Next
    INDEX
    Explanations

    "/imagine prompt:"

    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
    uant
    -0.09
    照
    -0.08
     unpopular
    -0.08
    Sen
    -0.08
     dismant
    -0.08
    RK
    -0.08
    tid
    -0.08
     Behandlung
    -0.08
     Raf
    -0.08
     unw
    -0.08
    POSITIVE LOGITS
    igen
    0.08
     syntax
    0.07
     emoji
    0.07
     synth
    0.07
     creative
    0.07
    ().
    0.07
     creativity
    0.07
     केली
    0.07
     synergy
    0.07
     instruction
    0.07
    Activations Density 0.025%

    No Known Activations