© 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. 11-RESID-POST-AA
    11. 45454
    Prev
    Next
    INDEX
    Explanations

    autos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ρεία
    -0.08
     pudd
    -0.08
     Dr
    -0.08
    ماع
    -0.07
     працы
    -0.07
    traditional
    -0.07
    Dr
    -0.07
     kelle
    -0.07
     rdr
    -0.07
    stringstream
    -0.07
    POSITIVE LOGITS
     необ
    0.07
    先
    0.07
    0.07
    .pro
    0.07
     fore
    0.07
     vi
    0.07
     תוכ
    0.07
    .beta
    0.07
     ๆ
    0.07
    _gamma
    0.07
    Activations Density 0.000%
    No Known Activations