Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47038
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    KES
    -0.09
     promos
    -0.08
     CASE
    -0.08
    (LOG
    -0.08
    uret
    -0.08
     ASSERT
    -0.08
    :YES
    -0.07
     Ene
    -0.07
    ոգ
    -0.07
     TEC
    -0.07
    POSITIVE LOGITS
     quasi
    0.08
     হিসাবে
    0.07
    သည်
    0.07
     �
    0.07
    ไว
    0.07
     น
    0.07
     Universität
    0.07
     ನ
    0.07
    -Ind
    0.07
     }}</
    0.07
    Activations Density 0.038%

    No Known Activations