© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50924
    Prev
    Next
    INDEX
    Explanations

    async, ng, and mat

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /:
    -0.10
    /{
    -0.09
    .module
    -0.09
    /home
    -0.08
    ("/{
    -0.08
    /student
    -0.08
     ARC
    -0.08
    senal
    -0.08
    /oct
    -0.08
    /$
    -0.08
    POSITIVE LOGITS
     async
    0.13
    async
    0.12
    mat
    0.11
    ng
    0.11
     Async
    0.11
     mat
    0.11
    Mat
    0.10
    _async
    0.10
    	async
    0.10
    Async
    0.10
    Activations Density 0.001%

    No Known Activations