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. 15-RESID-POST-AA
    6. 19584
    Prev
    Next
    INDEX
    Explanations

    10 or 100

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alternative
    -0.08
     nutric
    -0.07
     anomal
    -0.07
    พบ
    -0.07
     anat
    -0.07
    Annotated
    -0.07
    	stat
    -0.07
     paradox
    -0.07
     więc
    -0.07
    нор
    -0.07
    POSITIVE LOGITS
     atawa
    0.09
     utawa
    0.09
     큰
    0.08
     масштаб
    0.08
     või
    0.08
     atanapi
    0.08
     وڏ
    0.08
     Charity
    0.08
     ẹgbẹ
    0.08
    yeah
    0.08
    Activations Density 0.006%

    No Known Activations