© 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. 95586
    Prev
    Next
    INDEX
    Explanations

    fighter jets

    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
     managerial
    -0.08
     charity
    -0.08
    _rem
    -0.08
     punctuation
    -0.08
     hotel
    -0.07
    .rem
    -0.07
     intest
    -0.07
     ruin
    -0.07
     charities
    -0.07
     pooling
    -0.07
    POSITIVE LOGITS
     revamped
    0.10
     upgraded
    0.10
     Aerospace
    0.10
     unveiled
    0.10
     Airbus
    0.09
     radar
    0.09
     aerospace
    0.09
     helicopters
    0.09
     missile
    0.09
     flagship
    0.09
    Activations Density 0.028%

    No Known Activations