© 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. 99557
    Prev
    Next
    INDEX
    Explanations

    statistical distributions

    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
     conduz
    -0.09
     recorder
    -0.08
     بم
    -0.08
     markers
    -0.08
     ühend
    -0.08
    otl
    -0.07
     marking
    -0.07
    letal
    -0.07
    ęd
    -0.07
     unabhängig
    -0.07
    POSITIVE LOGITS
     overwhelmingly
    0.09
     defecto
    0.08
     Lands
    0.08
     fall
    0.08
     приходится
    0.08
     уд
    0.08
     ಹೆಚ್ಚು
    0.07
     বেশি
    0.07
    984
    0.07
    (Default
    0.07
    Activations Density 0.037%

    No Known Activations