© 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. 24858
    Prev
    Next
    INDEX
    Explanations

    Research and production

    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
     pataki
    -0.09
    çoit
    -0.08
     Oy
    -0.08
    Pare
    -0.08
    .nb
    -0.07
     คู่
    -0.07
    romyalgia
    -0.07
     الحكومية
    -0.07
    OTOS
    -0.07
    ávání
    -0.07
    POSITIVE LOGITS
     indist
    0.08
     pigment
    0.08
    023
    0.07
    Imper
    0.07
    jeni
    0.07
     tanda
    0.07
     Hutch
    0.07
     jenis
    0.07
     Lindsey
    0.07
     likeness
    0.07
    Activations Density 1.212%

    No Known Activations