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. 15-RESID-POST-AA
    6. 19114
    Prev
    Next
    INDEX
    Explanations

    Foreign 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
     qui
    -0.07
    upgrade
    -0.07
    ája
    -0.07
     cuentos
    -0.07
     adventures
    -0.07
     выращ
    -0.07
     exped
    -0.07
     visant
    -0.07
     changes
    -0.07
    다가
    -0.07
    POSITIVE LOGITS
     hyvä
    0.09
    ваць
    0.09
    աստան
    0.08
     ڪنهن
    0.08
    Signed
    0.08
     dessutom
    0.08
     Furthermore
    0.08
    innie
    0.08
    անս
    0.08
    יינער
    0.08
    Activations Density 0.020%

    No Known Activations