© 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. 26249
    Prev
    Next
    INDEX
    Explanations

    Engine

    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
    _daily
    -0.08
    Hourly
    -0.08
     ليلة
    -0.08
    فاق
    -0.08
    авання
    -0.07
    -night
    -0.07
    _mer
    -0.07
    -Service
    -0.07
    acier
    -0.07
    Revenue
    -0.07
    POSITIVE LOGITS
     zároveň
    0.08
     agrade
    0.07
    zuje
    0.07
     bh
    0.07
    ighbors
    0.07
    0.07
     Soc
    0.07
    ведите
    0.07
     convertible
    0.07
    ിക്കുക
    0.07
    Activations Density 0.001%

    No Known Activations