Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74692
    Prev
    Next
    INDEX
    Explanations

    Wait

    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
    aped
    -0.08
    rad
    -0.08
     تدري
    -0.07
     season
    -0.07
     drip
    -0.07
     combat
    -0.07
    Season
    -0.07
    Core
    -0.07
    (doc
    -0.07
     Penny
    -0.07
    POSITIVE LOGITS
     невер
    0.10
     Actually
    0.09
     계산
    0.09
     ísl
    0.08
     ntabwo
    0.08
     округ
    0.08
     hierbei
    0.08
    은행
    0.08
    Oops
    0.08
     киши
    0.08
    Activations Density 0.068%

    No Known Activations