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. 76421
    Prev
    Next
    INDEX
    Explanations

    DPI

    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
     idyllic
    -0.08
     sequ
    -0.08
     lith
    -0.08
     skeletal
    -0.07
     trama
    -0.07
     northern
    -0.07
     Mal
    -0.07
     puerto
    -0.07
    anut
    -0.07
     Dor
    -0.07
    POSITIVE LOGITS
    clarations
    0.09
     spreadsheets
    0.09
     PUBG
    0.09
    configured
    0.09
     нужна
    0.08
    。そして
    0.08
    'habitude
    0.08
     faucets
    0.08
     CONCAT
    0.08
    -search
    0.08
    Activations Density 0.001%

    No Known Activations