Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43068
    Prev
    Next
    INDEX
    Explanations

    5

    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
     asserting
    -0.08
     Noch
    -0.08
     स्थापित
    -0.08
    390
    -0.07
     तयार
    -0.07
     _$
    -0.07
     systematically
    -0.07
    834
    -0.07
    _ag
    -0.07
     মাধ্যম
    -0.07
    POSITIVE LOGITS
     hic
    0.08
    rawtypes
    0.07
     soy
    0.07
     otro
    0.07
     Alicia
    0.07
     beers
    0.07
    uploaded
    0.07
     Boise
    0.07
    don
    0.07
     עבור
    0.07
    Activations Density 0.188%

    No Known Activations