© 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. 47152
    Prev
    Next
    INDEX
    Explanations

    most

    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
     ок
    -0.08
    leden
    -0.07
    риг
    -0.07
    )
↵//
    -0.07
     құ
    -0.07
     contempt
    -0.07
     Ass
    -0.07
     hog
    -0.07
    oy
    -0.07
     Jones
    -0.07
    POSITIVE LOGITS
     aprovechar
    0.11
     aproveitar
    0.10
     Aprove
    0.09
     aprovech
    0.09
     afford
    0.09
     maximize
    0.08
    Ride
    0.08
     즐
    0.08
     Ride
    0.08
    าของ
    0.08
    Activations Density 0.010%

    No Known Activations