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. 88175
    Prev
    Next
    INDEX
    Explanations

    Multilingual text

    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
     noz
    -0.08
     Sein
    -0.08
     €,
    -0.07
     свеч
    -0.07
     maths
    -0.07
     прым
    -0.07
     aihe
    -0.07
    .server
    -0.07
    .footer
    -0.07
     €.
    -0.07
    POSITIVE LOGITS
     Viv
    0.08
     அ
    0.07
    0.07
    ^{-
    0.07
     powerless
    0.07
     infr
    0.07
    iada
    0.07
    ूर
    0.07
     muda
    0.07
     inaccurate
    0.07
    Activations Density 0.147%

    No Known Activations