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. 23-RESID-POST-AA
    6. 130718
    Prev
    Next
    INDEX
    Explanations

    ‌

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kl
    -0.08
    -placeholder
    -0.08
     G
    -0.07
     conform
    -0.07
     posit
    -0.07
     Humanos
    -0.07
     Pap
    -0.07
     ké
    -0.07
     Tr
    -0.07
     limb
    -0.07
    POSITIVE LOGITS
    gevo
    0.10
    ضيف
    0.10
    azụ
    0.09
    პ
    0.09
    0.08
     تقريب
    0.08
    _exists
    0.08
     asters
    0.08
     Gurbanguly
    0.08
    objc
    0.08
    Activations Density 0.001%

    No Known Activations