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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 53139
    Prev
    Next
    INDEX
    Explanations

    message

    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
    ikipedia
    -0.09
    érieur
    -0.09
     beeld
    -0.08
    .rgb
    -0.08
     brilliantly
    -0.08
    .jpeg
    -0.08
    ENO
    -0.08
    यान
    -0.08
     Guinness
    -0.08
     कोविड
    -0.08
    POSITIVE LOGITS
     общения
    0.11
     barter
    0.10
    交流
    0.10
     mailbox
    0.09
     вза
    0.09
     komunikasi
    0.09
     ileti
    0.09
     communication
    0.09
     التواصل
    0.09
     যোগাযোগ
    0.09
    Activations Density 0.015%

    No Known Activations