© 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. 47621
    Prev
    Next
    INDEX
    Explanations

    choices/options

    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
     cca
    -0.08
     babel
    -0.08
     tunn
    -0.08
     markdown
    -0.07
    -0.07
    Ө
    -0.07
    微信公众号
    -0.07
     aln
    -0.07
     Lenn
    -0.07
     uga
    -0.07
    POSITIVE LOGITS
    ವು
    0.08
     ಸ್ವ
    0.08
     vaardigheden
    0.07
    skill
    0.07
     ris
    0.07
     ambitious
    0.07
     Ony
    0.07
     يعود
    0.07
     성공
    0.07
    択
    0.07
    Activations Density 0.017%

    No Known Activations