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. 15-RESID-POST-AA
    6. 12
    Prev
    Next
    INDEX
    Explanations

    Plus or minus symbol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .redirect
    -0.09
    .Redirect
    -0.09
    Redirect
    -0.09
     کال
    -0.08
    uyến
    -0.08
     pediu
    -0.08
     Internet
    -0.08
    953
    -0.08
    segu
    -0.08
    Internet
    -0.07
    POSITIVE LOGITS
     ±
    0.15
     +/-
    0.14
     중심
    0.13
     કેન્દ્ર
    0.13
     ಕೇಂದ್ರ
    0.13
    ±
    0.13
    中心
    0.13
     కేంద్ర
    0.13
     центре
    0.13
     centered
    0.12
    Activations Density 0.023%

    No Known Activations