© 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. 702
    Prev
    Next
    INDEX
    Explanations

    contagious

    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
    innu
    -0.08
     paralle
    -0.08
     secours
    -0.07
    tere
    -0.07
    פק
    -0.07
    Mediator
    -0.07
    पाल
    -0.07
     רב
    -0.07
    ritt
    -0.07
     mount
    -0.07
    POSITIVE LOGITS
     enthusiasm
    0.13
     enthousiasme
    0.10
     laughter
    0.10
     enthusiastic
    0.09
     ಸೋಂಕ
    0.09
     infectious
    0.08
    感染
    0.08
     Deco
    0.08
    叫
    0.08
    魅
    0.08
    Activations Density 0.005%

    No Known Activations