© 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. 69845
    Prev
    Next
    INDEX
    Explanations

    markdown

    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
     관심
    -0.08
     slap
    -0.08
    ygon
    -0.08
    _SY
    -0.08
    -heading
    -0.07
    ocy
    -0.07
    Heading
    -0.07
     Возмож
    -0.07
     toes
    -0.07
     căn
    -0.07
    POSITIVE LOGITS
     Starbucks
    0.11
     automotive
    0.11
    航空
    0.10
     Pixar
    0.10
     renowned
    0.10
     airline
    0.10
     IKEA
    0.10
     Netflix
    0.10
     شركة
    0.09
     Google's
    0.09
    Activations Density 0.052%

    No Known Activations