© 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. 15-RESID-POST-AA
    11. 16323
    Prev
    Next
    INDEX
    Explanations

    variations of "ask"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depot
    -0.08
     professionele
    -0.08
    рофессион
    -0.08
     raid
    -0.08
    .Foundation
    -0.08
     professioneel
    -0.07
     realm
    -0.07
     innovatieve
    -0.07
    ಥ
    -0.07
    þ
    -0.07
    POSITIVE LOGITS
     asking
    0.13
     asked
    0.12
     phr
    0.12
     Asking
    0.12
     спраш
    0.12
     પૂછ
    0.12
     پوچھ
    0.11
     ചോദ
    0.11
     perguntar
    0.11
     Asked
    0.11
    Activations Density 0.080%

    No Known Activations