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. 49098
    Prev
    Next
    INDEX
    Explanations

    ай

    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
    Outline
    -0.08
    亦
    -0.08
    -The
    -0.08
     Investment
    -0.08
    -0.07
     embell
    -0.07
     investment
    -0.07
     adjustable
    -0.07
    采购
    -0.07
    IOS
    -0.07
    POSITIVE LOGITS
     retom
    0.10
     nuevamente
    0.09
     снова
    0.09
     продолжа
    0.09
    继续
    0.08
     continuar
    0.08
    تاب
    0.08
    _next
    0.08
    'z
    0.08
     pokrač
    0.08
    Activations Density 0.009%

    No Known Activations