© 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. 95490
    Prev
    Next
    INDEX
    Explanations

    vaccines

    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
     Anaheim
    -0.08
     unat
    -0.08
    xmlns
    -0.08
     Customers
    -0.08
    <Customer
    -0.07
     mauvaises
    -0.07
     rent
    -0.07
     doux
    -0.07
     ambience
    -0.07
     atrak
    -0.07
    POSITIVE LOGITS
     vaccines
    0.14
     vaccine
    0.13
    疫
    0.12
     antiviral
    0.12
    accine
    0.11
     pandemic
    0.11
     antibody
    0.10
     SARS
    0.10
     virus
    0.10
     пандем
    0.10
    Activations Density 0.012%

    No Known Activations