© 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. 23-RESID-POST-AA
    11. 49114
    Prev
    Next
    INDEX
    Explanations

    th

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilə
    -0.09
    imoine
    -0.09
     Fili
    -0.09
    ილი
    -0.08
    ИЛ
    -0.08
    iles
    -0.08
    ილო
    -0.08
     Everyday
    -0.08
    ილია
    -0.08
     بحر
    -0.08
    POSITIVE LOGITS
    ud
    0.17
    udding
    0.17
    und
    0.16
    uds
    0.16
    ump
    0.15
    umps
    0.15
    umping
    0.15
    umped
    0.14
    w
    0.14
    udd
    0.14
    Activations Density 0.002%

    No Known Activations