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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 145
    Prev
    Next
    INDEX
    Explanations

    "why" in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mga
    -0.08
    )->
    -0.08
     muy
    -0.08
    ummer
    -0.07
    íní
    -0.07
     kartaa
    -0.07
     ;↵
    -0.07
    `s
    -0.07
     jedenfalls
    -0.07
     )->
    -0.07
    POSITIVE LOGITS
     ఎంద
    0.17
     דווקא
    0.17
     why
    0.17
    这么
    0.16
     क्यों
    0.16
     এত
    0.16
     seemingly
    0.15
     为什么
    0.15
    如此
    0.15
     কেন
    0.15
    Activations Density 0.190%

    No Known Activations