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. 112840
    Prev
    Next
    INDEX
    Explanations

    William

    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
    kai
    -0.08
     kai
    -0.08
    here
    -0.08
     falling
    -0.08
     Kait
    -0.08
    der
    -0.07
     voc
    -0.07
     washed
    -0.07
    worthiness
    -0.07
     बताया
    -0.07
    POSITIVE LOGITS
     ah
    0.09
    ’t
    0.08
     Turner
    0.07
     exert
    0.07
    0.07
    	   
    0.07
     �
    0.07
     perfe
    0.07
     жел
    0.07
     teen
    0.07
    Activations Density 0.027%

    No Known Activations