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. 54067
    Prev
    Next
    INDEX
    Explanations

    for

    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
    ища
    -0.08
     destino
    -0.08
    (rename
    -0.08
     осв
    -0.08
    �
    -0.08
    र्मी
    -0.08
    स्थान
    -0.08
     Habitat
    -0.08
     habitation
    -0.07
    广
    -0.07
    POSITIVE LOGITS
    wie
    0.09
    comme
    0.09
     같이
    0.08
    vita
    0.08
    statement
    0.08
    vog
    0.08
    gul
    0.08
    ORES
    0.08
    tach
    0.08
    expr
    0.08
    Activations Density 0.003%

    No Known Activations