© 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. 108330
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
     Adelaide
    -0.08
     gre
    -0.08
    idon
    -0.07
     실
    -0.07
    wad
    -0.07
    https
    -0.07
    grep
    -0.07
    eps
    -0.07
    .fail
    -0.07
    enje
    -0.07
    POSITIVE LOGITS
     vanwege
    0.10
     besondere
    0.10
    _CONSTANT
    0.09
     leedahay
    0.09
    特殊
    0.09
     بسبب
    0.09
     besonderen
    0.08
     특별
    0.08
     CONSTANT
    0.08
     posee
    0.08
    Activations Density 0.089%

    No Known Activations