© 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. 7714
    Prev
    Next
    INDEX
    Explanations

    hash

    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
     deco
    -0.08
     включ
    -0.07
    preter
    -0.07
    Contents
    -0.07
    -0.07
     escalation
    -0.07
     少
    -0.07
     Alma
    -0.07
     Lippen
    -0.07
     HAR
    -0.07
    POSITIVE LOGITS
    .lookup
    0.08
     Möglichkeiten
    0.08
    桶
    0.07
    umbles
    0.07
    овые
    0.07
     stabilized
    0.07
     oordeel
    0.07
    еры
    0.07
     manfaat
    0.07
    .Keys
    0.07
    Activations Density 0.002%
    No Known Activations