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. 19250
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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
     agrade
    -0.08
     Perhaps
    -0.08
    ಂತಹ
    -0.08
    ldon
    -0.08
     경우
    -0.08
     Escorte
    -0.08
     confusion
    -0.07
     Provides
    -0.07
    よう
    -0.07
    adox
    -0.07
    POSITIVE LOGITS
    jší
    0.13
     oleva
    0.12
     seotud
    0.11
     இருக்கும்
    0.11
     بودن
    0.11
     இருந்து
    0.11
     представлены
    0.11
     ఉండ
    0.10
     olevan
    0.10
     থাকা
    0.10
    Activations Density 0.038%

    No Known Activations