© 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. 11-RESID-POST-AA
    11. 94427
    Prev
    Next
    INDEX
    Explanations

    government and politics

    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
    /math
    -0.08
     ambiance
    -0.08
    _rectangle
    -0.07
    Rectangle
    -0.07
    rectangle
    -0.07
    Metrics
    -0.07
     parche
    -0.07
    .Math
    -0.07
    Rect
    -0.07
    rect
    -0.07
    POSITIVE LOGITS
     missionary
    0.12
     diaspora
    0.12
     missionaries
    0.10
     transferência
    0.10
     विदेश
    0.10
     refugee
    0.10
     vlucht
    0.10
     humanitarian
    0.10
     해외
    0.10
     refugees
    0.09
    Activations Density 0.189%

    No Known Activations