© 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. 11-RESID-POST-AA
    6. 54537
    Prev
    Next
    INDEX
    Explanations

    $

    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
     basement
    -0.08
    Jesu
    -0.08
     nesse
    -0.08
     regula
    -0.07
     zvin
    -0.07
    Doors
    -0.07
    예
    -0.07
     bevel
    -0.07
     Integral
    -0.07
     integral
    -0.07
    POSITIVE LOGITS
     traduction
    0.10
     translated
    0.09
     USD
    0.09
     traduc
    0.09
     translating
    0.09
     traduit
    0.08
    洲
    0.08
     donated
    0.08
     donation
    0.08
     tradução
    0.08
    Activations Density 0.013%

    No Known Activations