© 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 EvalsExportsinterp-engineNEWAPI 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. 70743
    Prev
    Next
    INDEX
    Explanations

    B

    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
    /document
    -0.09
    arna
    -0.09
    anche
    -0.08
     continuity
    -0.08
    crawler
    -0.08
     World's
    -0.07
     Imagine
    -0.07
     statistically
    -0.07
    <typename
    -0.07
    ర్శ
    -0.07
    POSITIVE LOGITS
     �
    0.08
    ၊
    0.08
     Jun
    0.08
    その他
    0.08
     Tribe
    0.07
    եղ
    0.07
     嘉
    0.07
    ṭ
    0.07
    	L
    0.07
     ntev
    0.07
    Activations Density 0.025%

    No Known Activations