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. 88200
    Prev
    Next
    INDEX
    Explanations

    acrobat

    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
     aquarium
    -0.08
    Despite
    -0.08
     incarnation
    -0.08
     مادر
    -0.08
    _GPU
    -0.08
     accél
    -0.08
    Acceleration
    -0.08
    Plants
    -0.08
     organisms
    -0.08
     genetically
    -0.08
    POSITIVE LOGITS
    -hole
    0.09
     Adobe
    0.08
     kommentarer
    0.08
     Kommentare
    0.08
     Klein
    0.07
     Classic
    0.07
    yl
    0.07
     modifications
    0.07
    classic
    0.07
     Jordan
    0.07
    Activations Density 0.003%

    No Known Activations