© 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. 94342
    Prev
    Next
    INDEX
    Explanations

    circle

    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
     questionable
    -0.08
    estruct
    -0.07
     multif
    -0.07
    riz
    -0.07
    كي
    -0.07
    kező
    -0.07
     Americans
    -0.07
     dubious
    -0.07
    Can
    -0.07
     Sare
    -0.07
    POSITIVE LOGITS
    励
    0.08
    图库
    0.08
    іблі
    0.08
     fechado
    0.08
    中央
    0.08
    वरी
    0.08
    上的
    0.08
     trouvez
    0.08
     fech
    0.08
     populace
    0.08
    Activations Density 0.031%

    No Known Activations