© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    ratings

    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
     cresc
    -0.07
     pope
    -0.07
     poésie
    -0.07
     ungef
    -0.07
     geographically
    -0.07
     creciendo
    -0.07
    илей
    -0.07
     Bond
    -0.07
    apeut
    -0.07
     apa
    -0.07
    POSITIVE LOGITS
    客服
    0.08
    	display
    0.08
     회원
    0.08
    |null
    0.08
    	instance
    0.08
     목
    0.08
    會員
    0.08
     siding
    0.07
     Sax
    0.07
     lief
    0.07
    Activations Density 0.073%

    No Known Activations