© 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. 44313
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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
    itev
    -0.08
     rā
    -0.08
     पहिले
    -0.08
     निधन
    -0.08
     mbụ
    -0.07
     साह
    -0.07
    צה
    -0.07
     cohesive
    -0.07
    imwe
    -0.07
     pins
    -0.07
    POSITIVE LOGITS
     Umgang
    0.15
    扱
    0.13
     manipulating
    0.10
     dealings
    0.10
     manipulation
    0.10
    beitung
    0.09
     التعامل
    0.09
     Manip
    0.09
     обращаться
    0.09
     Verarbeitung
    0.09
    Activations Density 0.032%

    No Known Activations