© 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. 31421
    Prev
    Next
    INDEX
    Explanations

    open parenthesis

    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
     avid
    -0.07
    agnar
    -0.07
    urses
    -0.07
    ams
    -0.07
    可靠
    -0.07
     expertos
    -0.07
    ains
    -0.07
    pedia
    -0.07
     mim
    -0.07
     experts
    -0.07
    POSITIVE LOGITS
     происход
    0.08
     nazionale
    0.08
     disebut
    0.08
     trá
    0.08
    Так
    0.08
     controlador
    0.08
     மேல
    0.08
     название
    0.08
     মাঝ
    0.08
    controle
    0.08
    Activations Density 0.008%

    No Known Activations