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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 71208
    Prev
    Next
    INDEX
    Explanations

    GDPR Adequacy Decision

    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
     explicación
    -0.08
    结束
    -0.08
     പ്രത
    -0.08
     במ
    -0.08
    (Fragment
    -0.08
     daya
    -0.07
    ецца
    -0.07
    -ja
    -0.07
    举行
    -0.07
    疫
    -0.07
    POSITIVE LOGITS
     curated
    0.07
    Requirement
    0.07
     kel
    0.07
    Automation
    0.07
     российских
    0.07
    /".$
    0.07
    achadh
    0.07
     predefined
    0.07
    dddd
    0.07
     lighter
    0.07
    Activations Density 0.000%

    No Known Activations