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. 60842
    Prev
    Next
    INDEX
    Explanations

    formatting special characters

    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
    amag
    -0.10
    Arbe
    -0.08
    ledning
    -0.08
     fada
    -0.08
    hint
    -0.08
    ogas
    -0.08
    ология
    -0.07
    (j
    -0.07
    フォ
    -0.07
     dirig
    -0.07
    POSITIVE LOGITS
     Requires
    0.09
     Weddings
    0.09
     Might
    0.08
     Stars
    0.08
     Use
    0.08
     Begin
    0.08
    との
    0.08
     Neither
    0.08
     Beware
    0.07
    .tb
    0.07
    Activations Density 0.028%

    No Known Activations