© 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. 29257
    Prev
    Next
    INDEX
    Explanations

    auxiliary

    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
    рис
    -0.08
    سم
    -0.08
    lais
    -0.07
    [X
    -0.07
    uta
    -0.07
    unning
    -0.07
    :=
    -0.07
    ta
    -0.07
     needle
    -0.07
    .DES
    -0.07
    POSITIVE LOGITS
     accompagne
    0.09
     accompagné
    0.09
     없이
    0.09
     сопровож
    0.08
     accompagner
    0.08
     véhicule
    0.08
    article
    0.08
     accompan
    0.08
    oxi
    0.08
    陪
    0.08
    Activations Density 0.001%

    No Known Activations