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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70344
    Prev
    Next
    INDEX
    Explanations

    elegant

    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
    不上
    -0.11
    TYPE
    -0.09
    FFFFFFFF
    -0.09
    采取
    -0.08
    _THRESH
    -0.08
    ્ચ
    -0.08
    atge
    -0.08
    不到
    -0.08
     Verbraucher
    -0.08
    عتها
    -0.07
    POSITIVE LOGITS
    _solution
    0.08
     платформ
    0.08
     фотографии
    0.08
     colorful
    0.07
    摄影
    0.07
     cruis
    0.07
     ег
    0.07
    _sid
    0.07
     flamb
    0.07
     vibrant
    0.07
    Activations Density 0.006%

    No Known Activations