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. 43947
    Prev
    Next
    INDEX
    Explanations

    comparative

    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
    感じ
    -0.08
     плане
    -0.08
    spiele
    -0.08
     сторону
    -0.08
    quette
    -0.08
    shirts
    -0.08
    舔
    -0.08
    ointe
    -0.08
    机关
    -0.08
     kautta
    -0.08
    POSITIVE LOGITS
     million
    0.10
     dozen
    0.10
     hundreds
    0.09
     millions
    0.09
     thousand
    0.09
    655
    0.09
    625
    0.09
     thousands
    0.09
    864
    0.08
     hundred
    0.08
    Activations Density 0.063%

    No Known Activations