© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63424
    Prev
    Next
    INDEX
    Explanations

    varies by location

    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
    /posts
    -0.08
    ְ
    -0.08
     ether
    -0.07
     appreh
    -0.07
    Separate
    -0.07
     આત
    -0.07
    tà
    -0.07
     sépar
    -0.07
     separados
    -0.07
    	comp
    -0.07
    POSITIVE LOGITS
     wildly
    0.09
     sterk
    0.09
     depending
    0.09
    depending
    0.08
    -अलग
    0.08
     vary
    0.08
     sizin
    0.08
     varies
    0.08
     sõlt
    0.08
     בהתאם
    0.08
    Activations Density 0.035%

    No Known Activations