© 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. 13341
    Prev
    Next
    INDEX
    Explanations

    Eck

    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
     Gug
    -0.08
    ?”
    -0.08
    违
    -0.08
     singer
    -0.08
     violation
    -0.07
    !”
    -0.07
    ὸ
    -0.07
     assistant
    -0.07
    іні
    -0.07
    'u
    -0.07
    POSITIVE LOGITS
     vala
    0.08
     Sheep
    0.08
    ाटन
    0.08
    भार
    0.08
    bh
    0.07
     kraj
    0.07
    Breadcrumb
    0.07
     cleans
    0.07
    ltä
    0.07
    Loading
    0.07
    Activations Density 0.001%

    No Known Activations