© 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. 3-RESID-POST-AA
    11. 13045
    Prev
    Next
    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Montage
    -0.09
     Pob
    -0.08
     Craw
    -0.08
     FIN
    -0.08
     Heidelberg
    -0.08
     Zusch
    -0.08
     পাব
    -0.08
     Kina
    -0.07
     Noah
    -0.07
     beob
    -0.07
    POSITIVE LOGITS
    丝
    0.08
    Val
    0.08
     refrigeration
    0.08
    aran
    0.08
    wrap
    0.08
     الواحد
    0.08
    낼
    0.07
    wrapped
    0.07
    �
    0.07
    aur
    0.07
    Activations Density 0.005%

    No Known Activations