© 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. 29237
    Prev
    Next
    INDEX
    Explanations

    urge

    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
    ваются
    -0.08
    ailand
    -0.08
    .Ok
    -0.08
    berichte
    -0.08
    шая
    -0.08
     assembly
    -0.07
    tyard
    -0.07
    /security
    -0.07
     ok
    -0.07
    veloppement
    -0.07
    POSITIVE LOGITS
     compelled
    0.11
     urge
    0.10
     इच्छा
    0.09
     către
    0.09
     urges
    0.09
     craving
    0.09
     insisting
    0.09
     compelling
    0.08
     compuls
    0.08
     आग्रह
    0.08
    Activations Density 0.014%

    No Known Activations