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. 111798
    Prev
    Next
    INDEX
    Explanations

    plus or length

    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
     Tuesday
    -0.08
    weekly
    -0.07
     Monday
    -0.07
     monday
    -0.07
     year
    -0.07
     call
    -0.07
     monthly
    -0.07
    	call
    -0.07
    	Mat
    -0.07
     Ries
    -0.07
    POSITIVE LOGITS
     EXTRA
    0.09
     odstran
    0.08
    Removed
    0.08
     ikaw
    0.08
    _extra
    0.08
     extra
    0.08
     buildup
    0.08
    removed
    0.08
     containment
    0.08
     twice
    0.08
    Activations Density 0.017%

    No Known Activations