© 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. 94361
    Prev
    Next
    INDEX
    Explanations

    period

    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
     litigation
    -0.08
    SSH
    -0.08
    endidos
    -0.08
     esprit
    -0.08
    amiliar
    -0.08
     Sally
    -0.08
     sall
    -0.08
     sildenafil
    -0.08
     ವರ್�
    -0.08
     Litigation
    -0.07
    POSITIVE LOGITS
     negligible
    0.09
     tiny
    0.09
     minute
    0.09
     needle
    0.08
    000
    0.08
     hay
    0.08
     chút
    0.08
    Tiny
    0.08
    tiny
    0.08
    080
    0.08
    Activations Density 0.030%

    No Known Activations