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. 29819
    Prev
    Next
    INDEX
    Explanations

    Low angle emphasize

    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
    _locations
    -0.10
     સ્થળ
    -0.09
     locations
    -0.09
     પ્રકાર
    -0.09
     ಸ್ಥಳ
    -0.09
    Locations
    -0.08
     સ્થાન
    -0.08
     استخراج
    -0.08
    _datetime
    -0.08
    _sites
    -0.08
    POSITIVE LOGITS
     towering
    0.11
     height
    0.10
    HEIGHT
    0.10
    .Height
    0.10
    (height
    0.10
     taller
    0.10
    	height
    0.09
     looming
    0.09
     вверх
    0.09
    height
    0.09
    Activations Density 0.007%

    No Known Activations