Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48397
    Prev
    Next
    INDEX
    Explanations

    J

    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
     γίνεται
    -0.09
     γίνει
    -0.09
     mö
    -0.09
     ott
    -0.09
     məsəl
    -0.08
     tois
    -0.08
     galima
    -0.08
     dónde
    -0.08
     έγινε
    -0.08
    -0.08
    POSITIVE LOGITS
    end
    0.11
    ender
    0.11
    enuh
    0.10
    arak
    0.10
    erman
    0.10
    utaan
    0.10
    eda
    0.09
    antung
    0.09
    enius
    0.09
    aringan
    0.09
    Activations Density 0.000%

    No Known Activations