© 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. 13132
    Prev
    Next
    INDEX
    Explanations

    Japanese language/culture

    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
     tendência
    -0.08
     pru
    -0.08
    -0.07
    cur
    -0.07
     பட்ட
    -0.07
    Elizabeth
    -0.07
    ப்பட்ட
    -0.07
     ukuy
    -0.07
     suíte
    -0.07
    .cur
    -0.07
    POSITIVE LOGITS
     rendement
    0.08
    acce
    0.08
     �
    0.07
     Ono
    0.07
    -spec
    0.07
     aument
    0.07
     appreh
    0.07
     Rend
    0.07
     rela
    0.07
     embl
    0.07
    Activations Density 0.003%
    No Known Activations