© 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. 103365
    Prev
    Next
    INDEX
    Explanations

    each

    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
     per
    -0.09
    нила
    -0.09
    нить
    -0.08
    ится
    -0.08
     buffer
    -0.08
     termasuk
    -0.08
    ویه
    -0.08
    кортостан
    -0.08
    ნება
    -0.08
     нескольких
    -0.08
    POSITIVE LOGITS
     each
    0.22
    ，每
    0.22
    each
    0.21
    (each
    0.20
    Each
    0.20
     Each
    0.19
     chacun
    0.19
     chacune
    0.19
     cada
    0.19
     mỗi
    0.19
    Activations Density 0.095%

    No Known Activations