© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29106
    Prev
    Next
    INDEX
    Explanations

    Driving visibility

    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
     feminist
    -0.08
     copier
    -0.08
     stolen
    -0.07
     molé
    -0.07
     polymers
    -0.07
     needs
    -0.07
     रिश्त
    -0.07
     feminism
    -0.07
     accession
    -0.07
     copied
    -0.07
    POSITIVE LOGITS
    驾驶
    0.15
     സുരക്ഷ
    0.13
     safety
    0.13
     Safety
    0.13
     безопасность
    0.12
    veilig
    0.12
     안전
    0.12
     veiligheids
    0.12
    安全
    0.12
     turvall
    0.12
    Activations Density 0.072%

    No Known Activations