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. 48746
    Prev
    Next
    INDEX
    Explanations

    fluffy

    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
     tariff
    -0.09
     Sole
    -0.08
     også
    -0.08
     العالي
    -0.08
     ymin
    -0.08
     بالإضافة
    -0.08
     slechts
    -0.08
     Mere
    -0.08
     sheegay
    -0.07
    новременно
    -0.07
    POSITIVE LOGITS
     physically
    0.08
    -knit
    0.08
    
    0.08
     loops
    0.08
     textures
    0.07
     open
    0.07
     footprints
    0.07
     fís
    0.07
     ridd
    0.07
     nicely
    0.07
    Activations Density 0.006%

    No Known Activations