© 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. 19-RESID-POST-AA
    11. 103274
    Prev
    Next
    INDEX
    Explanations

    stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     핵
    -0.08
     Db
    -0.08
     lucrative
    -0.08
     các
    -0.08
    utele
    -0.08
     blijkbaar
    -0.08
    和
    -0.08
     وڌيڪ
    -0.08
    (key
    -0.08
     beneficial
    -0.08
    POSITIVE LOGITS
     nonfiction
    0.10
     গল্প
    0.09
     excerpts
    0.09
     рассказ
    0.09
    ‑
    0.09
    	title
    0.09
     కథ
    0.09
     കഥ
    0.08
    —not
    0.08
     небольшой
    0.08
    Activations Density 0.040%

    No Known Activations