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. 90123
    Prev
    Next
    INDEX
    Explanations

    positive

    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
     PLA
    -0.08
     国家
    -0.08
     licensed
    -0.08
    批准
    -0.07
    -so
    -0.07
     approve
    -0.07
     FSC
    -0.07
     canned
    -0.07
    approved
    -0.07
    �િત
    -0.07
    POSITIVE LOGITS
     diminishing
    0.10
     enää
    0.09
    aryti
    0.09
    ocytes
    0.08
    ications
    0.08
     decreasing
    0.08
     beyond
    0.08
    Increasing
    0.07
    Beyond
    0.07
     хуже
    0.07
    Activations Density 0.094%

    No Known Activations