© 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 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. 63993
    Prev
    Next
    INDEX
    Explanations

    Future correspondence in messages

    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
     asks
    -0.10
     fordert
    -0.09
     求
    -0.09
    uchtet
    -0.08
     fatig
    -0.08
    求
    -0.08
    "<
    -0.08
     усе
    -0.07
    (cp
    -0.07
    verte
    -0.07
    POSITIVE LOGITS
     forthcoming
    0.16
     القادمة
    0.13
     Upcoming
    0.13
     upcoming
    0.12
     आगामी
    0.11
     예정
    0.11
    Upcoming
    0.11
     próxim
    0.11
     binnenkort
    0.11
     soon
    0.11
    Activations Density 0.127%

    No Known Activations