© 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. 63808
    Prev
    Next
    INDEX
    Explanations

    So

    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
     anyway
    -0.09
    ળી
    -0.08
     --->
    -0.08
     bhu
    -0.08
    pole
    -0.08
     simp
    -0.08
     yaitu
    -0.08
     anyways
    -0.08
     reveals
    -0.08
     Pada
    -0.08
    POSITIVE LOGITS
     Risks
    0.10
     risks
    0.09
    ’in
    0.09
    .ke
    0.08
     interdisciplinary
    0.08
     تضم
    0.08
    'in
    0.08
     Meister
    0.08
     priorit
    0.08
     Bestseller
    0.07
    Activations Density 0.012%

    No Known Activations