© 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. 30830
    Prev
    Next
    INDEX
    Explanations

    lion

    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
    nom
    -0.07
     Sor
    -0.07
     Hoch
    -0.07
    _ls
    -0.07
     cobalt
    -0.07
     Lá
    -0.07
     parity
    -0.07
     Pb
    -0.07
    curse
    -0.07
    Pb
    -0.07
    POSITIVE LOGITS
     véritable
    0.10
     настоящий
    0.09
     charismatic
    0.09
     troupe
    0.09
     군
    0.08
    陵
    0.08
     rampant
    0.08
    袖
    0.08
    群
    0.08
    Afr
    0.08
    Activations Density 0.005%

    No Known Activations