© 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. 13244
    Prev
    Next
    INDEX
    Explanations

    most

    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
     지
    -0.07
    Made
    -0.07
    .Exceptions
    -0.07
     examines
    -0.07
     범
    -0.07
     exceptions
    -0.07
    跨度
    -0.07
     Made
    -0.07
     రంగ
    -0.07
     тур
    -0.07
    POSITIVE LOGITS
    mess
    0.08
     إست
    0.07
    ിലും
    0.07
    dsl
    0.07
     bose
    0.07
    _inc
    0.07
    Optimal
    0.07
     Optimal
    0.07
     lay
    0.07
    نال
    0.07
    Activations Density 0.043%

    No Known Activations