© 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. 19-RESID-POST-AA
    11. 102405
    Prev
    Next
    INDEX
    Explanations

    say Async

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     What
    -0.10
     what
    -0.09
     But
    -0.08
     Are
    -0.08
    What
    -0.08
     Both
    -0.08
     Define
    -0.08
     usan
    -0.08
     both
    -0.08
     define
    -0.08
    POSITIVE LOGITS
    Async
    0.24
    _async
    0.23
    async
    0.17
     asynchronously
    0.17
     Async
    0.17
    	async
    0.16
    .async
    0.16
     asynchronous
    0.16
     async
    0.15
    .Async
    0.14
    Activations Density 0.001%

    No Known Activations