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. 111
    Prev
    Next
    INDEX
    Explanations

    programming file types

    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
     artist
    -0.08
     fana
    -0.08
    agentur
    -0.08
     queer
    -0.08
     warto
    -0.08
    نور
    -0.08
     athlete
    -0.08
     artiste
    -0.08
     equitable
    -0.08
     gymnast
    -0.08
    POSITIVE LOGITS
    .exe
    0.13
     VBA
    0.09
    (HWND
    0.09
    (hwnd
    0.09
     Professional
    0.09
    .dll
    0.08
     المفت
    0.08
     Intelli
    0.08
    .Ribbon
    0.08
    ®
    0.08
    Activations Density 0.010%

    No Known Activations