© 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. 68659
    Prev
    Next
    INDEX
    Explanations

    obtaining

    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
    ක
    -0.08
    Counters
    -0.07
    cych
    -0.07
     curate
    -0.07
     composing
    -0.07
    .loaded
    -0.07
    cer
    -0.07
     ознакомиться
    -0.07
     geleg
    -0.07
    Represent
    -0.07
    POSITIVE LOGITS
    lambda
    0.08
     Sida
    0.08
    ว่า
    0.08
     lambda
    0.08
     निकाल
    0.08
     получается
    0.08
    nię
    0.08
     élég
    0.08
     மக
    0.08
     Juvent
    0.07
    Activations Density 0.037%

    No Known Activations