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. 15-RESID-POST-AA
    6. 19074
    Prev
    Next
    INDEX
    Explanations

    video

    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
     SQLite
    -0.08
    439
    -0.08
     immigrant
    -0.08
     sympathetic
    -0.08
     Sofa
    -0.08
     hippoc
    -0.08
    abled
    -0.08
    ‌బ
    -0.07
    bian
    -0.07
     traveler
    -0.07
    POSITIVE LOGITS
     videoclip
    0.13
     visuals
    0.11
     영상
    0.11
    (song
    0.11
     वायरल
    0.10
     वीडियो
    0.10
     lyrics
    0.10
     വീഡിയോ
    0.10
     vídeos
    0.10
    視頻
    0.10
    Activations Density 0.020%

    No Known Activations