© 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. 13181
    Prev
    Next
    INDEX
    Explanations

    faulty

    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
     preset
    -0.08
    Ten
    -0.07
    味
    -0.07
     viewer
    -0.07
    енты
    -0.07
     distinctions
    -0.07
     cz
    -0.07
    (strategy
    -0.07
    �
    -0.07
     ten
    -0.07
    POSITIVE LOGITS
     Mir
    0.08
    _mc
    0.08
     सडक
    0.08
     carc
    0.08
    culate
    0.08
     sok
    0.08
     specialise
    0.08
    ekele
    0.08
     plc
    0.07
     kinda
    0.07
    Activations Density 0.001%

    No Known Activations