© 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. 24845
    Prev
    Next
    INDEX
    Explanations

    desires

    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
     অথবা
    -0.08
     고
    -0.08
     suggestions
    -0.08
     Suggested
    -0.07
     allowing
    -0.07
    Oder
    -0.07
     obowią
    -0.07
    ्ल
    -0.07
     subdivision
    -0.07
     suggested
    -0.07
    POSITIVE LOGITS
     desirable
    0.12
     strives
    0.12
     seeks
    0.11
     coveted
    0.10
     streven
    0.10
     strive
    0.10
     aims
    0.09
     desires
    0.09
     objectives
    0.09
     aim
    0.09
    Activations Density 0.092%

    No Known Activations