© 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. 11-RESID-POST-AA
    6. 54598
    Prev
    Next
    INDEX
    Explanations

    merged cells

    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
     discipline
    -0.08
     demons
    -0.08
     disciplined
    -0.08
     Healthy
    -0.08
    暴
    -0.08
     healthy
    -0.08
     Discipline
    -0.07
     gezonde
    -0.07
    _vectors
    -0.07
    kor
    -0.07
    POSITIVE LOGITS
     rowspan
    0.15
     colspan
    0.13
    :grid
    0.09
     multin
    0.09
     diagon
    0.08
    merged
    0.08
    uang
    0.08
     spanning
    0.08
     overlapping
    0.08
    块
    0.08
    Activations Density 0.003%

    No Known Activations