© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 94716
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    hä
    -0.08
     doctorate
    -0.08
    लोड
    -0.07
     Quan
    -0.07
     Routing
    -0.07
    抢
    -0.07
     soins
    -0.07
    -0.07
     bulld
    -0.07
     democrático
    -0.07
    POSITIVE LOGITS
    ULATION
    0.09
    _PRODUCT
    0.09
    _SER
    0.09
     blah
    0.08
     calculus
    0.08
    OURCE
    0.08
     �
    0.07
     təş
    0.07
    த்திர
    0.07
    _DEF
    0.07
    Activations Density 0.016%
    No Known Activations