© 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. 3-RESID-POST-AA
    11. 983
    Prev
    Next
    INDEX
    Explanations

    copper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invol
    -0.08
    قان
    -0.07
     соб
    -0.07
     Kun
    -0.07
     Paw
    -0.07
    ાની
    -0.07
     robes
    -0.07
     renal
    -0.07
     cartilage
    -0.07
     woo
    -0.07
    POSITIVE LOGITS
     tesis
    0.08
     Want
    0.07
     tsl
    0.07
     Ox
    0.07
    矿
    0.07
     дор
    0.07
    Slash
    0.07
    Meth
    0.07
     Teen
    0.07
    lotte
    0.07
    Activations Density 0.005%

    No Known Activations