© 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. 64466
    Prev
    Next
    INDEX
    Explanations

    defense mechanisms

    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
     LUT
    -0.08
     fundamentals
    -0.07
    寝
    -0.07
     PIT
    -0.07
    江
    -0.07
     principles
    -0.07
    athon
    -0.07
     선정
    -0.07
     hunt
    -0.07
     finesse
    -0.07
    POSITIVE LOGITS
     protect
    0.09
     protects
    0.09
     mutil
    0.09
     حماية
    0.08
     Protect
    0.08
    防
    0.08
     outspoken
    0.08
    保护
    0.08
     protéger
    0.08
     huiles
    0.08
    Activations Density 0.011%

    No Known Activations