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. 11916
    Prev
    Next
    INDEX
    Explanations

    display

    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
     forgiveness
    -0.09
     Cancel
    -0.08
    Async
    -0.08
     Encore
    -0.08
    Cancel
    -0.08
     Fuj
    -0.08
     Inflation
    -0.07
     Outlook
    -0.07
     رابطه
    -0.07
     conception
    -0.07
    POSITIVE LOGITS
    展示
    0.15
     präsentieren
    0.12
     Präsent
    0.12
     präsentiert
    0.11
     प्रस्त
    0.11
     presenteren
    0.11
     ಪ್ರದ
    0.11
    display
    0.11
     tentoon
    0.11
     presentations
    0.10
    Activations Density 0.040%

    No Known Activations