© 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. 19-RESID-POST-AA
    11. 103552
    Prev
    Next
    INDEX
    Explanations

    insulation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Genome
    -0.08
     genome
    -0.08
     recurring
    -0.08
    受付
    -0.08
    Recurring
    -0.08
     unmittelbar
    -0.08
     Genome
    -0.07
     marquee
    -0.07
    Bookmark
    -0.07
     desfile
    -0.07
    POSITIVE LOGITS
     insulation
    0.32
     insulating
    0.27
     утеп
    0.24
     insulated
    0.23
     isolamento
    0.22
     aislamiento
    0.21
     izol
    0.20
    隔
    0.19
    изоля
    0.19
     aisl
    0.18
    Activations Density 0.020%

    No Known Activations