Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 58608
    Prev
    Next
    INDEX
    Explanations

    ist

    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
     com
    -0.08
    key
    -0.07
    connecting
    -0.07
     Pl
    -0.07
     Ward
    -0.07
     An
    -0.07
    ipper
    -0.07
    plast
    -0.07
    b
    -0.07
    master
    -0.07
    POSITIVE LOGITS
    !!!
    0.10
    !!!↵↵
    0.10
    !?
    0.10
    ?↵↵
    0.09
    ونډ
    0.09
    😉
    0.09
     downright
    0.09
    -have
    0.09
     كذلك
    0.09
     LN
    0.09
    Activations Density 0.125%

    No Known Activations