© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 63113
    Prev
    Next
    INDEX
    Explanations

    cybersecurity

    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
    舒
    -0.08
    ursor
    -0.08
     comfortable
    -0.08
    cules
    -0.08
     hitter
    -0.07
     díky
    -0.07
     Through
    -0.07
    cule
    -0.07
     uncomfortable
    -0.07
     comfort
    -0.07
    POSITIVE LOGITS
     vulnerabilities
    0.11
     ആക്രമ
    0.10
     attaques
    0.10
     હુમ
    0.10
     আটক
    0.09
     ransomware
    0.09
     saldır
    0.09
     দুর
    0.09
     vuln
    0.09
     flaws
    0.09
    Activations Density 0.017%

    No Known Activations