© 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. 54321
    Prev
    Next
    INDEX
    Explanations

    vi

    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
     asbestos
    -0.08
     euro
    -0.08
     yom
    -0.08
     bunk
    -0.08
     wool
    -0.08
     hive
    -0.08
     employers
    -0.07
     sneaker
    -0.07
    �
    -0.07
     warehouse
    -0.07
    POSITIVE LOGITS
    pendicular
    0.09
    ilie
    0.09
     множ
    0.09
     personalizado
    0.08
    .Return
    0.08
     personalizada
    0.08
    กรรม
    0.08
     personnalisé
    0.08
    .Prepared
    0.08
    .Student
    0.08
    Activations Density 0.002%

    No Known Activations