© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2721
    Prev
    Next
    INDEX
    Explanations

    charts

    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
    อนไ
    -0.08
    乾
    -0.08
     therm
    -0.07
    idir
    -0.07
     tér
    -0.07
     entfer
    -0.07
    Adr
    -0.07
     Magistr
    -0.07
     SIG
    -0.07
     FIND
    -0.07
    POSITIVE LOGITS
     italic
    0.08
    percent
    0.08
     उद्ध
    0.08
    粗
    0.08
    0.08
     Dollar
    0.08
     hatch
    0.08
    _PERCENT
    0.08
     ₹
    0.07
     Sea
    0.07
    Activations Density 0.003%
    No Known Activations