© 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. 31404
    Prev
    Next
    INDEX
    Explanations

    m and n

    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
     Lösungen
    -0.08
     soluções
    -0.08
     transformations
    -0.08
     solutions
    -0.08
     শন
    -0.08
     solusi
    -0.08
     حلول
    -0.08
     Solutions
    -0.08
     рішення
    -0.08
     decisões
    -0.08
    POSITIVE LOGITS
    B
    0.08
    _strlen
    0.08
    Mismatch
    0.07
    Totals
    0.07
    Longest
    0.07
    sizes
    0.07
    Also
    0.07
    Lis
    0.07
    event
    0.07
    Idi
    0.07
    Activations Density 0.017%

    No Known Activations