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. 30012
    Prev
    Next
    INDEX
    Explanations

    URE

    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
    Customize
    -0.09
    Customized
    -0.08
    ைப்
    -0.08
     करे
    -0.08
    burst
    -0.08
    -sheet
    -0.07
     தனது
    -0.07
    Mol
    -0.07
    Vir
    -0.07
     Richter
    -0.07
    POSITIVE LOGITS
     controversy
    0.08
     stepping
    0.08
    (input
    0.08
    (expected
    0.07
    isses
    0.07
     squeezing
    0.07
     حس
    0.07
    	input
    0.07
     none
    0.07
     quite
    0.07
    Activations Density 0.000%

    No Known Activations