© 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 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. 69220
    Prev
    Next
    INDEX
    Explanations

    reduces; simplification

    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
     고
    -0.08
     crushed
    -0.08
     dismissal
    -0.08
     proche
    -0.08
     каж
    -0.07
     이후
    -0.07
    dismiss
    -0.07
    予定
    -0.07
    .dismiss
    -0.07
    robes
    -0.07
    POSITIVE LOGITS
     investigate
    0.09
     überlegen
    0.09
    寻找
    0.09
     investigates
    0.09
     estimating
    0.08
     investigating
    0.08
     알아
    0.08
     analyze
    0.08
     endeavor
    0.08
     Aufgabe
    0.08
    Activations Density 0.044%

    No Known Activations