© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51725
    Prev
    Next
    INDEX
    Explanations

    Russian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    има
    -0.09
    маны
    -0.09
    ениями
    -0.09
     sedi
    -0.09
    ements
    -0.09
     recordar
    -0.08
     publicar
    -0.08
    મ
    -0.08
    'aimer
    -0.08
     sere
    -0.08
    POSITIVE LOGITS
     ihres
    0.08
    -ab
    0.07
     Wege
    0.07
    ZD
    0.07
     sie
    0.07
     electron
    0.07
     bomba
    0.07
     Ab
    0.07
     trọng
    0.07
     diese
    0.07
    Activations Density 0.001%

    No Known Activations