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. 26664
    Prev
    Next
    INDEX
    Explanations

    read

    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
     coleg
    -0.08
     иници
    -0.08
     ઉજ
    -0.07
     célébr
    -0.07
    (Create
    -0.07
     celebrates
    -0.07
    	Collections
    -0.07
    Celebr
    -0.07
    举
    -0.07
    >Create
    -0.07
    POSITIVE LOGITS
     внимательно
    0.13
     thoroughly
    0.12
    仔
    0.12
    阅读
    0.11
     comprehension
    0.10
     deten
    0.10
     ознакомиться
    0.10
     阅读
    0.10
     comprehend
    0.09
     familiarize
    0.09
    Activations Density 0.034%

    No Known Activations