© 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. 79263
    Prev
    Next
    INDEX
    Explanations

    opy

    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
     mime
    -0.09
     coro
    -0.08
     cab
    -0.07
     intégr
    -0.07
    /render
    -0.07
    mime
    -0.07
     artistas
    -0.07
     unset
    -0.07
     belum
    -0.07
     dbl
    -0.07
    POSITIVE LOGITS
     PTSD
    0.09
     prosecution
    0.09
    ethol
    0.09
    Provincia
    0.09
    uhake
    0.09
     scar
    0.08
    yeah
    0.08
    Las
    0.08
     tuge
    0.08
     گزار
    0.08
    Activations Density 0.000%

    No Known Activations