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. 12822
    Prev
    Next
    INDEX
    Explanations

    number

    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
     almost
    -0.09
     Almost
    -0.09
    almost
    -0.08
     거의
    -0.08
     quase
    -0.08
     практически
    -0.08
    'is
    -0.08
     почти
    -0.07
    perate
    -0.07
    avic
    -0.07
    POSITIVE LOGITS
    დათ
    0.08
    Qty
    0.08
    kehrt
    0.08
     qty
    0.08
     عدد
    0.08
    త్స
    0.08
    -ended
    0.08
     paradox
    0.08
    _qty
    0.08
     मात्रा
    0.08
    Activations Density 0.025%

    No Known Activations