© 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. 47668
    Prev
    Next
    INDEX
    Explanations

    each

    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
    201
    -0.08
     au
    -0.08
    ._
    -0.07
    fl
    -0.07
    _equ
    -0.07
    ey
    -0.07
    219
    -0.07
     firsthand
    -0.07
    078
    -0.07
    041
    -0.07
    POSITIVE LOGITS
     preferência
    0.09
     spacing
    0.09
     persever
    0.09
     apresentação
    0.09
     préférence
    0.08
     Preference
    0.08
    ให
    0.08
    spacing
    0.08
     بأس
    0.08
     preference
    0.08
    Activations Density 0.003%

    No Known Activations