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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129482
    Prev
    Next
    INDEX
    Explanations

    Hacking and Security Concerns

    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
     जिल
    -0.10
     Nursing
    -0.10
     Insurance
    -0.10
    Women's
    -0.09
     dispense
    -0.09
     impover
    -0.09
    _shipping
    -0.08
     Handicap
    -0.08
     dilute
    -0.08
     राहत
    -0.08
    POSITIVE LOGITS
     cybersecurity
    0.14
     attackers
    0.14
     malware
    0.13
     hackers
    0.13
     antivirus
    0.12
     hacker
    0.12
     malicious
    0.12
     ransomware
    0.11
     remediation
    0.11
     hacking
    0.11
    Activations Density 0.019%

    No Known Activations