© 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. 3-RESID-POST-AA
    11. 1027
    Prev
    Next
    INDEX
    Explanations

    ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mast
    -0.09
     constitutional
    -0.08
    旨
    -0.08
    wreck
    -0.07
    -0.07
    ël
    -0.07
    יצ
    -0.07
    üren
    -0.07
     настоящ
    -0.07
    .intellij
    -0.07
    POSITIVE LOGITS
     Bro
    0.08
     LIV
    0.08
     liv
    0.08
     Sylvia
    0.08
     अर
    0.07
     Liv
    0.07
     फाय
    0.07
     SY
    0.07
    Bro
    0.07
     plane
    0.07
    Activations Density 0.052%
    No Known Activations