© 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. 13454
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Myself
    -0.11
    sab
    -0.07
    domin
    -0.07
     sab
    -0.07
     Epstein
    -0.07
     Witt
    -0.07
     rapidez
    -0.07
     produced
    -0.07
     Cra
    -0.07
     retard
    -0.07
    POSITIVE LOGITS
     Hollow
    0.08
     карт
    0.08
     integrante
    0.08
    muş
    0.07
     hollow
    0.07
    cement
    0.07
     Mauritius
    0.07
     আস
    0.07
     �
    0.07
     aesthetic
    0.07
    Activations Density 0.025%

    No Known Activations