© 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. 48041
    Prev
    Next
    INDEX
    Explanations

    safety incidents

    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
    -0.08
     العمل
    -0.08
     direction
    -0.08
     Mediterr
    -0.07
     French
    -0.07
    قة
    -0.07
    dict
    -0.07
     irrigation
    -0.07
     genital
    -0.07
     ваш
    -0.07
    POSITIVE LOGITS
     iniciativas
    0.09
    Thunk
    0.09
     ঘটে
    0.08
    akus
    0.08
    525
    0.08
     ఘటన
    0.08
     initiatives
    0.08
     Plast
    0.08
    Occurrence
    0.08
     idées
    0.08
    Activations Density 0.002%
    No Known Activations