© 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. 47113
    Prev
    Next
    INDEX
    Explanations

    research, investigation

    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
    опас
    -0.08
     ifade
    -0.07
    ANGLE
    -0.07
    (Dense
    -0.07
     deform
    -0.07
     critics
    -0.07
    point
    -0.07
     гол
    -0.07
     RESET
    -0.07
     Tic
    -0.07
    POSITIVE LOGITS
     조사
    0.12
    Gather
    0.11
     gathering
    0.11
     gather
    0.10
     researched
    0.10
     approfond
    0.10
     gathered
    0.10
     levantamento
    0.10
    调查
    0.10
     researching
    0.10
    Activations Density 0.061%

    No Known Activations