© 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. 103413
    Prev
    Next
    INDEX
    Explanations

    权

    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
     často
    -0.08
    톤
    -0.08
     often
    -0.07
    λώ
    -0.07
    ्दी
    -0.07
     chl
    -0.07
     иногда
    -0.07
     sedikit
    -0.07
     sometimes
    -0.07
     outras
    -0.07
    POSITIVE LOGITS
    fully
    0.12
    ৃপ
    0.11
    ેત્ર
    0.11
    ilege
    0.11
    ৃত্ব
    0.10
    ORITY
    0.10
    衡
    0.10
    orship
    0.10
    ileges
    0.09
    lessness
    0.09
    Activations Density 0.003%

    No Known Activations