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. 88035
    Prev
    Next
    INDEX
    Explanations

    math word problems

    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
    Bearing
    -0.08
    	cin
    -0.08
     bearing
    -0.08
    -bearing
    -0.07
    )(↵
    -0.07
     attachment
    -0.07
     attire
    -0.07
    ware
    -0.07
     calling
    -0.07
    રુ
    -0.07
    POSITIVE LOGITS
     therefore
    0.08
    Quoted
    0.08
     размеры
    0.08
     இட
    0.08
     adaml
    0.07
     தற்போது
    0.07
     quindi
    0.07
     cuál
    0.07
    Â
    0.07
    ‡
    0.07
    Activations Density 0.117%

    No Known Activations