© 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. 78223
    Prev
    Next
    INDEX
    Explanations

    Puzzles and strategies

    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
    keä
    -0.08
    opi
    -0.08
    وتر
    -0.07
     Giz
    -0.07
    epi
    -0.07
    eps
    -0.07
     Glock
    -0.07
    Telegram
    -0.07
     erros
    -0.07
     Gewer
    -0.07
    POSITIVE LOGITS
     predetermined
    0.11
     заранее
    0.09
     beforehand
    0.09
     מראש
    0.09
     predefined
    0.08
    [R
    0.08
    matige
    0.08
    ,R
    0.08
    éanmoins
    0.08
    ))),
    0.08
    Activations Density 0.004%

    No Known Activations