© 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. 23-RESID-POST-AA
    11. 49098
    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fapt
    -0.09
     koliko
    -0.09
     ogni
    -0.08
     ejus
    -0.08
     చెప్ప
    -0.08
     kaiken
    -0.08
     faktiskt
    -0.08
     шиг
    -0.08
     zeigen
    -0.08
     известно
    -0.08
    POSITIVE LOGITS
     solutions
    0.14
     possibilities
    0.14
     Solutions
    0.14
     soluções
    0.13
    Solutions
    0.13
     roots
    0.13
    Option
    0.13
     possibility
    0.13
    solutions
    0.12
    option
    0.12
    Activations Density 0.122%

    No Known Activations