© 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. 11-RESID-POST-AA
    11. 69930
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     питания
    -0.08
     Kron
    -0.08
     diffraction
    -0.08
     Protest
    -0.08
     питание
    -0.08
     chanc
    -0.08
    �
    -0.08
     beve
    -0.08
     plurality
    -0.08
    🏼
    -0.08
    POSITIVE LOGITS
     emitting
    0.08
     brink
    0.08
     intox
    0.08
     رسید
    0.08
     الأفضل
    0.08
     nyata
    0.08
     victory
    0.07
     breakthroughs
    0.07
     لتحقيق
    0.07
     المستوى
    0.07
    Activations Density 0.030%

    No Known Activations