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. 60835
    Prev
    Next
    INDEX
    Explanations

    skin on

    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
     verlangen
    -0.08
     расход
    -0.08
     regiment
    -0.07
     kond
    -0.07
    μό
    -0.07
     Verst
    -0.07
     Erklärung
    -0.07
    ヤ
    -0.07
     Vietnam
    -0.07
     Ordnung
    -0.07
    POSITIVE LOGITS
     intact
    0.11
    -inclusive
    0.11
     ambience
    0.08
     باقی
    0.08
     Included
    0.08
    აულ
    0.08
     inclus
    0.08
    ೇಜ
    0.08
     retained
    0.08
    Included
    0.08
    Activations Density 0.020%

    No Known Activations