© 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. 2981
    Prev
    Next
    INDEX
    Explanations

    shapes

    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
     aktif
    -0.08
     мест
    -0.08
     nač
    -0.08
     Tacoma
    -0.08
    Roy
    -0.07
    wx
    -0.07
     ikon
    -0.07
     Rav
    -0.07
     hil
    -0.07
     conséquence
    -0.07
    POSITIVE LOGITS
     Schwar
    0.09
    mdb
    0.09
     Kirch
    0.08
    ड
    0.08
    èi
    0.07
     Obrig
    0.07
    iów
    0.07
    üü
    0.07
     KIND
    0.07
     Tub
    0.07
    Activations Density 0.067%

    No Known Activations