© 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. 111372
    Prev
    Next
    INDEX
    Explanations

    Mathematical intervals

    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
     ك
    -0.08
    ledu
    -0.08
     seri
    -0.08
     authentic
    -0.07
     Clover
    -0.07
     Hertz
    -0.07
     pedigree
    -0.07
     bun
    -0.07
    58
    -0.07
     будь
    -0.07
    POSITIVE LOGITS
    वरी
    0.09
     modifiers
    0.08
    ATA
    0.08
    သူ
    0.08
    mai
    0.08
     гг
    0.08
     eingesch
    0.08
    উ
    0.08
    -low
    0.08
     માલ
    0.08
    Activations Density 0.017%

    No Known Activations