© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    Каж

    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
    구
    -0.07
     Ei
    -0.07
     QE
    -0.07
     Obs
    -0.07
     Bình
    -0.07
    chn
    -0.07
    dst
    -0.07
     Hom
    -0.07
     име
    -0.07
     Komm
    -0.07
    POSITIVE LOGITS
     pata
    0.08
     sen
    0.08
     convincing
    0.08
    agara
    0.07
    Rack
    0.07
     laminated
    0.07
     vom
    0.07
     assort
    0.07
     pur
    0.07
     perm
    0.07
    Activations Density 0.000%

    No Known Activations