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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 56135
    Prev
    Next
    INDEX
    Explanations

    fictional

    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
    Outer
    -0.08
    _outer
    -0.08
    Chron
    -0.08
    .plugin
    -0.08
    Här
    -0.08
    outer
    -0.08
    .username
    -0.07
     같은
    -0.07
     المحت
    -0.07
    Here
    -0.07
    POSITIVE LOGITS
     reproduction
    0.09
     stripper
    0.09
     partik
    0.08
     baka
    0.08
     Overrides
    0.08
     gaa
    0.08
     repro
    0.08
     inu
    0.08
    _REMOVE
    0.07
     HG
    0.07
    Activations Density 0.005%

    No Known Activations