Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58981
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    jung
    -0.07
    [[
    -0.07
     Probate
    -0.07
     Vertical
    -0.07
    -direct
    -0.07
     Stable
    -0.07
    __;↵↵
    -0.07
    Vertical
    -0.07
    Certified
    -0.07
     повед
    -0.07
    POSITIVE LOGITS
     વગેરે
    0.12
     usw
    0.10
     എന്നിവ
    0.10
     आदि
    0.10
     എന്നീ
    0.10
    直到
    0.09
    等等
    0.09
     וכו
    0.09
     തുടങ്ങിയ
    0.09
     hatta
    0.09
    Activations Density 0.045%

    No Known Activations