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. 65183
    Prev
    Next
    INDEX
    Explanations

    readers/audience

    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
    rn
    -0.09
    သော
    -0.09
    ті
    -0.09
    λλα
    -0.08
     等
    -0.08
     അന്ത
    -0.07
    담
    -0.07
     reproduc
    -0.07
     シ
    -0.07
    αλ
    -0.07
    POSITIVE LOGITS
    和值
    0.08
     complexes
    0.07
     maximise
    0.07
    0.07
    *innen
    0.07
     rica
    0.07
     skeptical
    0.07
    *v
    0.07
     Homem
    0.07
     iray
    0.07
    Activations Density 0.013%

    No Known Activations