© 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. 54409
    Prev
    Next
    INDEX
    Explanations

    serialization formats

    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
    ipat
    -0.08
     lockdown
    -0.08
    Retail
    -0.08
     LED
    -0.08
    County
    -0.08
    pies
    -0.08
    Municip
    -0.08
    灯
    -0.08
    Nike
    -0.08
     Prada
    -0.08
    POSITIVE LOGITS
    serialization
    0.14
     serialization
    0.14
    .serialize
    0.14
     сериал
    0.13
    Serialization
    0.13
     serde
    0.13
     serialize
    0.13
    serde
    0.13
    .serialization
    0.13
    serialize
    0.13
    Activations Density 0.011%

    No Known Activations