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. 48995
    Prev
    Next
    INDEX
    Explanations

    -sectional

    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
     fleet
    -0.08
     giờ
    -0.08
    执行
    -0.08
    \htdocs
    -0.08
    -0.07
    écution
    -0.07
     º
    -0.07
     senses
    -0.07
     proverb
    -0.07
     Hang
    -0.07
    POSITIVE LOGITS
    pere
    0.08
    levels
    0.08
    MH
    0.07
    وافق
    0.07
     seviy
    0.07
    equal
    0.07
    pag
    0.07
     صحة
    0.07
    ivit
    0.07
    asuring
    0.07
    Activations Density 0.000%

    No Known Activations