© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64443
    Prev
    Next
    INDEX
    Explanations

    quiz questions

    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
     beskr
    -0.09
    Ware
    -0.08
    kat
    -0.08
    vite
    -0.08
    structured
    -0.08
    充分
    -0.08
     observe
    -0.07
    _dx
    -0.07
    .observe
    -0.07
     advocating
    -0.07
    POSITIVE LOGITS
     trivia
    0.19
     Trivia
    0.18
    Trivia
    0.14
     quiz
    0.12
    竞猜
    0.12
     Quiz
    0.11
    答
    0.11
     memorabilia
    0.11
     Encycl
    0.11
    Quiz
    0.11
    Activations Density 0.116%

    No Known Activations