© 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 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. 43038
    Prev
    Next
    INDEX
    Explanations

    safety and emergency

    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
    Marketing
    -0.09
    Calendar
    -0.09
    .Cookie
    -0.09
    есто
    -0.08
    Hotel
    -0.08
     lunes
    -0.08
     pescado
    -0.08
     Calendar
    -0.08
    Customize
    -0.08
    Breakfast
    -0.08
    POSITIVE LOGITS
     safety
    0.15
     safeguards
    0.14
     Safety
    0.14
     авар
    0.13
     안전
    0.13
     safeguard
    0.13
    Safety
    0.12
     safeguarding
    0.11
     Saf
    0.11
    _safe
    0.11
    Activations Density 0.018%

    No Known Activations