© 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. 51033
    Prev
    Next
    INDEX
    Explanations

    Points

    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
     prévue
    -0.11
     entspricht
    -0.10
     prevista
    -0.10
     prévu
    -0.09
     vorgesehen
    -0.09
    ена
    -0.08
     correspondiente
    -0.08
     omvat
    -0.08
     예상
    -0.08
    jalo
    -0.08
    POSITIVE LOGITS
     clés
    0.16
     sa
    0.12
    Not
    0.11
    -cl
    0.11
    Mar
    0.11
     retenir
    0.11
    Sa
    0.11
     claves
    0.10
     not
    0.10
     les
    0.10
    Activations Density 0.014%

    No Known Activations