© 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. 95700
    Prev
    Next
    INDEX
    Explanations

    integrated technology

    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
     полов
    -0.08
    十五
    -0.07
    leground
    -0.07
     пон
    -0.07
     acus
    -0.07
    や
    -0.07
     sophomore
    -0.07
     runaway
    -0.07
    半年
    -0.07
    奉
    -0.07
    POSITIVE LOGITS
     встро
    0.11
     integriert
    0.10
     functionalities
    0.10
     incorpora
    0.09
     attached
    0.09
     기능
    0.09
     programmable
    0.09
     funcionalidades
    0.09
     fonctionnalités
    0.09
     embedded
    0.09
    Activations Density 0.069%

    No Known Activations