© 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. 112672
    Prev
    Next
    INDEX
    Explanations

    6

    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
     muted
    -0.09
     ASEAN
    -0.08
     martial
    -0.08
     θ
    -0.07
    .Constant
    -0.07
    yin
    -0.07
     enclosing
    -0.07
     zone
    -0.07
     adeeg
    -0.07
     ω
    -0.07
    POSITIVE LOGITS
    _Print
    0.08
    ERA
    0.08
    нан
    0.08
     Printer
    0.08
    _CHAR
    0.08
    _PREF
    0.07
    _Header
    0.07
     Username
    0.07
    కం
    0.07
     Glam
    0.07
    Activations Density 0.002%

    No Known Activations