© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    playground

    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
     Valencia
    -0.08
     seguida
    -0.08
    untza
    -0.07
    ezing
    -0.07
     sensed
    -0.07
     minorities
    -0.07
    Val
    -0.07
    েস
    -0.07
     Sylvia
    -0.07
     గొ
    -0.07
    POSITIVE LOGITS
    insen
    0.08
    сид
    0.07
     вним
    0.07
    ندی
    0.07
    iseid
    0.07
     procure
    0.07
     отк
    0.07
     чинов
    0.07
     Toe
    0.07
    כי
    0.07
    Activations Density 0.001%

    No Known Activations