© 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. 7-RESID-POST-AA
    6. 1082
    Prev
    Next
    INDEX
    Explanations

    yan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lapping
    -0.08
    PACK
    -0.07
     Wilmington
    -0.07
     Strip
    -0.07
     liking
    -0.07
     சார
    -0.07
     aiment
    -0.07
    -Pack
    -0.07
    _CONTROLLER
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Dha
    0.11
     lời
    0.09
     fháil
    0.09
    ónicas
    0.09
     feng
    0.08
     søker
    0.08
    dha
    0.08
     conseiller
    0.08
     Borges
    0.08
     ntawm
    0.08
    Activations Density 0.000%

    No Known Activations