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. 77435
    Prev
    Next
    INDEX
    Explanations

    выше

    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
     génération
    -0.09
    akuha
    -0.08
    ained
    -0.07
     examine
    -0.07
    _dx
    -0.07
     shifting
    -0.07
     Ba
    -0.07
    oinhos
    -0.07
    olite
    -0.07
     }\
    -0.07
    POSITIVE LOGITS
    Ignored
    0.09
    QUIT
    0.08
    وفي
    0.08
     leyes
    0.08
     بتاريخ
    0.08
    ्रा
    0.08
    த்திய
    0.08
     ضرور
    0.08
    GRESS
    0.08
    zan
    0.08
    Activations Density 0.001%

    No Known Activations