© 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. 95716
    Prev
    Next
    INDEX
    Explanations

    six

    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
    bn
    -0.08
     Через
    -0.08
     frecuencia
    -0.08
     afdeling
    -0.08
     соз
    -0.08
     danış
    -0.08
     kembali
    -0.07
    ousand
    -0.07
     Министер
    -0.07
    cko
    -0.07
    POSITIVE LOGITS
     violence
    0.08
    Shard
    0.08
     greeting
    0.08
     pragmatic
    0.08
     lock
    0.08
     Phaser
    0.07
     violência
    0.07
     vim
    0.07
     Locke
    0.07
     violencia
    0.07
    Activations Density 0.000%

    No Known Activations