© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20943
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     प्रति
    -0.10
     cadrul
    -0.09
     peł
    -0.09
    bagai
    -0.09
    itemap
    -0.08
     perkembangan
    -0.08
     rámci
    -0.08
    iled
    -0.08
    ajemen
    -0.08
     pentru
    -0.08
    POSITIVE LOGITS
     cosine
    0.09
     взаимодейств
    0.09
     interference
    0.09
     cos
    0.09
     আন্ত
    0.08
    Interaction
    0.08
     Cos
    0.08
     الاتصال
    0.08
    cos
    0.08
    -inter
    0.08
    Activations Density 0.015%

    No Known Activations