© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25978
    Prev
    Next
    INDEX
    Explanations

    system

    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
     lenght
    -0.08
     nueva
    -0.07
    .zip
    -0.07
    .Zip
    -0.07
     suffice
    -0.07
    føring
    -0.07
    umeric
    -0.07
    Costo
    -0.07
     Zentral
    -0.07
    .Det
    -0.07
    POSITIVE LOGITS
    <|channel|>
    0.09
    -meta
    0.08
     guideline
    0.08
     чат
    0.08
    /meta
    0.08
    вод
    0.08
     قالت
    0.08
     hala
    0.08
     ог
    0.08
    akaʻi
    0.08
    Activations Density 0.002%

    No Known Activations