Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112118
    Prev
    Next
    INDEX
    Explanations

    Titanic

    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
     rotates
    -0.09
     promoting
    -0.08
     tir
    -0.08
     benchmarks
    -0.07
     permission
    -0.07
     elected
    -0.07
     rotate
    -0.07
     liberated
    -0.07
    (rotation
    -0.07
     rotations
    -0.07
    POSITIVE LOGITS
     কিং
    0.08
    Era
    0.08
     леген
    0.08
      		
    0.08
     높
    0.08
     era
    0.08
     apparition
    0.08
    -era
    0.08
    		 
    0.08
     большин
    0.08
    Activations Density 0.003%

    No Known Activations