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. 76062
    Prev
    Next
    INDEX
    Explanations

    ем

    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
     fehlt
    -0.09
     Neck
    -0.08
     Turn
    -0.08
    .turn
    -0.08
    .Dictionary
    -0.08
     flera
    -0.08
     ekonom
    -0.08
    Finance
    -0.07
    Turn
    -0.07
    Lots
    -0.07
    POSITIVE LOGITS
     spirit
    0.08
     	
    0.08
     блю
    0.08
    柱
    0.08
     сал
    0.08
    imiento
    0.08
     പത
    0.08
     	 
    0.08
     гармони
    0.07
    Hx
    0.07
    Activations Density 0.001%

    No Known Activations