© 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. 63225
    Prev
    Next
    INDEX
    Explanations

    still

    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
     collaboration
    -0.08
     Collaboration
    -0.08
     disclosures
    -0.07
     uninsured
    -0.07
    Managers
    -0.07
     Foster
    -0.07
     aí
    -0.07
    .verbose
    -0.07
    伙
    -0.07
     fantastische
    -0.07
    POSITIVE LOGITS
    静
    0.11
     serene
    0.09
     शांत
    0.09
     calm
    0.09
    -state
    0.09
     demeanor
    0.08
     serenity
    0.08
     спокой
    0.08
     tranqu
    0.08
    -motion
    0.08
    Activations Density 0.006%

    No Known Activations