© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 3116
    Prev
    Next
    INDEX
    Explanations

    jective

    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
     Hammond
    -0.09
     Humph
    -0.08
    imoto
    -0.08
    毛
    -0.08
    林
    -0.07
    tz
    -0.07
    Philip
    -0.07
    gung
    -0.07
    -enable
    -0.07
    finger
    -0.07
    POSITIVE LOGITS
     ആ
    0.08
     sech
    0.08
     centered
    0.07
     lief
    0.07
    icka
    0.07
     STD
    0.07
     accom
    0.07
     stringify
    0.07
    0.07
     appreci
    0.07
    Activations Density 0.002%

    No Known Activations