© 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. 111221
    Prev
    Next
    INDEX
    Explanations

    flooring

    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
     unidos
    -0.08
     الوحدة
    -0.08
     scattered
    -0.08
     CO
    -0.07
     coher
    -0.07
     unity
    -0.07
     los
    -0.07
     unify
    -0.07
     года
    -0.07
    عيد
    -0.07
    POSITIVE LOGITS
     trafic
    0.13
    Traffic
    0.13
     traffic
    0.12
    traffic
    0.12
     verkeer
    0.12
     trafik
    0.12
     Traffic
    0.11
     traff
    0.11
     tráfico
    0.11
     readership
    0.10
    Activations Density 0.023%

    No Known Activations