© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 102238
    Prev
    Next
    INDEX
    Explanations

    **

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -0.11
    :↵↵
    -0.10
    ：
    -0.09
    ;
    -0.09
    ，如果
    -0.09
    （
    -0.08
    —for
    -0.08
    :↵
    -0.08
    ;;
    -0.08
    ：（
    -0.08
    POSITIVE LOGITS
     nature
    0.16
    Purpose
    0.16
     Purpose
    0.16
     purpose
    0.16
     Nature
    0.15
    Nature
    0.15
     finalidade
    0.14
     natureza
    0.14
     naturaleza
    0.14
    purpose
    0.13
    Activations Density 0.042%

    No Known Activations