© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 3034
    Prev
    Next
    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chill
    -0.08
     wolf
    -0.08
     inc
    -0.07
     gray
    -0.07
     pirate
    -0.07
    mouse
    -0.07
     phantom
    -0.07
     fr
    -0.07
    free
    -0.07
     weld
    -0.07
    POSITIVE LOGITS
    ுடன்
    0.08
     البيان
    0.08
    بود
    0.08
    ению
    0.08
     Enlight
    0.08
    _bucket
    0.08
    _documents
    0.07
     Gesundheits
    0.07
    STORE
    0.07
     hitta
    0.07
    Activations Density 0.001%

    No Known Activations