© 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. 69328
    Prev
    Next
    INDEX
    Explanations

    table

    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
     judiciary
    -0.09
    俄
    -0.08
    ongoose
    -0.08
    /operator
    -0.08
    trecht
    -0.08
    rito
    -0.08
    Covid
    -0.08
    oulder
    -0.08
    	operator
    -0.08
     tarj
    -0.07
    POSITIVE LOGITS
     cellpadding
    0.15
     cellspacing
    0.14
     rowspan
    0.09
     bgcolor
    0.09
     हु
    0.09
     nowrap
    0.08
     xmlns
    0.08
     Cun
    0.08
     Rodney
    0.08
     boast
    0.08
    Activations Density 0.004%

    No Known Activations