© 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. 30460
    Prev
    Next
    INDEX
    Explanations

    explosion

    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
    eva
    -0.08
     passport
    -0.07
    िका
    -0.07
    *↵//
    -0.07
    -0.07
    461
    -0.07
    .Editor
    -0.07
    ிக
    -0.07
     loan
    -0.07
    vania
    -0.07
    POSITIVE LOGITS
    巨
    0.10
     ঘট
    0.09
     explosion
    0.09
    事故
    0.08
     violently
    0.08
     巨
    0.08
     fizz
    0.08
     adrenaline
    0.08
     لم
    0.08
     combust
    0.08
    Activations Density 0.017%
    No Known Activations