© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45346
    Prev
    Next
    INDEX
    Explanations

    math

    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
    。また
    -0.09
    ’є
    -0.08
    。此外
    -0.08
    。そして
    -0.08
     EXIST
    -0.08
    常委
    -0.08
     papier
    -0.08
     qat
    -0.08
     wichtigste
    -0.08
    -0.08
    POSITIVE LOGITS
    .tem
    0.07
     naman
    0.07
    uwen
    0.07
    ütz
    0.07
    oss
    0.07
    upu
    0.07
    ipu
    0.07
     ọ
    0.07
    cute
    0.07
     म्हणजे
    0.07
    Activations Density 0.395%

    No Known Activations