© 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. 78231
    Prev
    Next
    INDEX
    Explanations

    home environment

    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
    _shadow
    -0.09
     Coalition
    -0.08
     coat
    -0.08
     obedience
    -0.08
     shadow
    -0.08
    -shadow
    -0.08
     coalition
    -0.08
    包
    -0.07
     cuota
    -0.07
     Конт
    -0.07
    POSITIVE LOGITS
     hemma
    0.12
     stationary
    0.12
     zuhause
    0.10
     server
    0.10
    服务器
    0.10
     hjemme
    0.10
     בבית
    0.10
     дома
    0.09
     Hause
    0.09
    _Statics
    0.09
    Activations Density 0.184%

    No Known Activations