© 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. 13406
    Prev
    Next
    INDEX
    Explanations

    raf

    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
     peanuts
    -0.09
    ोह
    -0.08
     절
    -0.08
     호텔
    -0.08
     Pregnancy
    -0.08
     स्टार
    -0.08
     غذا
    -0.08
     مط
    -0.08
     Heidel
    -0.08
     Star
    -0.07
    POSITIVE LOGITS
     project
    0.08
     fiss
    0.08
     Workspace
    0.08
    .xr
    0.07
     vinn
    0.07
    ESH
    0.07
    elar
    0.07
     llvm
    0.07
    esh
    0.07
     whai
    0.07
    Activations Density 0.000%

    No Known Activations