© 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. 99156
    Prev
    Next
    INDEX
    Explanations

    autopsy and death reports

    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
     שמת
    -0.08
     rally
    -0.08
     ظه
    -0.08
     الأه
    -0.08
     scalable
    -0.08
    utha
    -0.08
     પ્રય
    -0.08
     elastic
    -0.07
     વિસ્તારમાં
    -0.07
     immobil
    -0.07
    POSITIVE LOGITS
    검
    0.09
    piar
    0.08
     검사
    0.08
     findings
    0.08
    otomy
    0.08
    人體
    0.08
     forensic
    0.08
     mirac
    0.08
     examinations
    0.08
     corporis
    0.08
    Activations Density 0.005%

    No Known Activations