© 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. 988
    Prev
    Next
    INDEX
    Explanations

    mathematical derivations/contradictions

    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
    —for
    -0.08
    ##_
    -0.07
     speculate
    -0.07
    ارف
    -0.07
     justify
    -0.07
     thumbnail
    -0.07
    haven
    -0.07
    Authors
    -0.07
     perceived
    -0.07
     ಅವ
    -0.07
    POSITIVE LOGITS
     Kari
    0.09
     Sut
    0.08
    ww
    0.08
    ంటే
    0.08
     Sic
    0.08
     Gui
    0.08
    -flow
    0.08
     Bik
    0.08
     bipartisan
    0.08
     Nut
    0.08
    Activations Density 0.061%

    No Known Activations