© 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. 68211
    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
    __:
    -0.09
    quently
    -0.08
     guards
    -0.08
     admit
    -0.08
    (that
    -0.08
    .SDK
    -0.08
    .API
    -0.07
     suppose
    -0.07
    .chunk
    -0.07
    .Recycler
    -0.07
    POSITIVE LOGITS
     terrorist
    0.12
     espion
    0.11
     extremist
    0.11
     phishing
    0.11
     propaganda
    0.10
     sovereign
    0.10
     북한
    0.10
     malicious
    0.10
     Patriot
    0.09
     trolling
    0.09
    Activations Density 0.031%

    No Known Activations