© 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. 75617
    Prev
    Next
    INDEX
    Explanations

    acrostic

    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
     रहने
    -0.07
     thermostat
    -0.07
     onderscheiden
    -0.07
     paginator
    -0.07
    awa
    -0.07
     gure
    -0.07
     Herman
    -0.07
    ു�
    -0.07
     expériment
    -0.07
     competence
    -0.07
    POSITIVE LOGITS
     解
    0.09
    解
    0.09
     字
    0.09
    /modules
    0.08
    זרת
    0.08
    jado
    0.08
     мист
    0.08
     vividly
    0.08
    andaş
    0.08
     至
    0.08
    Activations Density 0.009%

    No Known Activations