© 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. 3105
    Prev
    Next
    INDEX
    Explanations

    content

    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
     transforme
    -0.09
     Zig
    -0.08
     tore
    -0.07
     يت
    -0.07
     rama
    -0.07
     μετα
    -0.07
     ALERT
    -0.07
     transformations
    -0.07
     Leap
    -0.07
     Paw
    -0.07
    POSITIVE LOGITS
    .Item
    0.07
    我
    0.07
     वाट
    0.07
    Item
    0.07
    .SC
    0.07
    FM
    0.07
     hydro
    0.07
     pretending
    0.07
    您
    0.07
     నీ
    0.07
    Activations Density 0.000%

    No Known Activations