© 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. 51766
    Prev
    Next
    INDEX
    Explanations

    un

    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
    ité
    -0.10
     servir
    -0.08
    idades
    -0.08
    வில்லை
    -0.08
    ită
    -0.08
    ுகள்
    -0.08
     година
    -0.08
     sirve
    -0.08
     살
    -0.08
     cité
    -0.08
    POSITIVE LOGITS
     tant
    0.12
     po
    0.11
     tanto
    0.10
    ifiés
    0.09
    ificado
    0.09
    Pois
    0.09
    ific
    0.09
     pouco
    0.08
    ificada
    0.08
     peu
    0.08
    Activations Density 0.001%

    No Known Activations