© 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. 11-RESID-POST-AA
    11. 111499
    Prev
    Next
    INDEX
    Explanations

    convey

    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
     compares
    -0.09
     dispon
    -0.08
    /ext
    -0.07
    ling
    -0.07
    380
    -0.07
     fashioned
    -0.07
     Faz
    -0.07
    -0.07
     descarg
    -0.07
    tbl
    -0.07
    POSITIVE LOGITS
     intentions
    0.10
    什么意思
    0.10
     convey
    0.10
     intent
    0.10
     conveyed
    0.10
     urgency
    0.09
     vermitteln
    0.09
     intangible
    0.09
     conveying
    0.09
     خی
    0.08
    Activations Density 0.010%
    No Known Activations