© 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. 108247
    Prev
    Next
    INDEX
    Explanations

    Human behavior and stories

    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
     dijeron
    -0.08
    нда
    -0.08
     Say
    -0.08
    .Nombre
    -0.08
     Adri
    -0.08
     пен
    -0.07
     say
    -0.07
    .gz
    -0.07
    .descripcion
    -0.07
     подроб
    -0.07
    POSITIVE LOGITS
     instinct
    0.13
     prefers
    0.10
     humain
    0.09
     instincts
    0.09
     prefer
    0.09
     preferential
    0.09
     subconscious
    0.09
     craving
    0.09
     crave
    0.09
    prefer
    0.09
    Activations Density 0.105%

    No Known Activations