© 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. 1111
    Prev
    Next
    INDEX
    Explanations

    sted

    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
    ære
    -0.08
    ére
    -0.07
     corriente
    -0.07
     correctamente
    -0.07
     Severe
    -0.07
     SE
    -0.07
     граждан
    -0.07
     языке
    -0.07
     excepcional
    -0.07
    ection
    -0.07
    POSITIVE LOGITS
     pastel
    0.08
     faded
    0.08
    -gray
    0.08
     ceramic
    0.08
    curve
    0.08
    -muted
    0.08
     frosting
    0.08
     skim
    0.08
     toned
    0.08
     muted
    0.08
    Activations Density 0.002%

    No Known Activations