© 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. 31140
    Prev
    Next
    INDEX
    Explanations

    reduce traffic/emissions

    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
     neve
    -0.08
     Weather
    -0.08
     ಅವಕಾಶ
    -0.08
     ಆಯ
    -0.08
     favorable
    -0.08
    -weather
    -0.07
     Correction
    -0.07
    -sama
    -0.07
     ಉದ
    -0.07
    Correction
    -0.07
    POSITIVE LOGITS
     crimes
    0.09
     violence
    0.08
     террор
    0.08
    .destroy
    0.08
     delitos
    0.08
    ાંડ
    0.08
     Crimes
    0.08
     crime
    0.07
     delito
    0.07
     rozm
    0.07
    Activations Density 0.006%

    No Known Activations