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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102852
    Prev
    Next
    INDEX
    Explanations

    numbers in other languages

    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
    esterday
    -0.08
     honderd
    -0.08
     seventy
    -0.08
    stdb
    -0.08
     sixty
    -0.08
    .'/'.$
    -0.07
    venty
    -0.07
     schön
    -0.07
    ноним
    -0.07
     ох
    -0.07
    POSITIVE LOGITS
     zahlreichen
    0.10
    6
    0.10
     numerosos
    0.10
     numerosas
    0.09
     六
    0.09
     zahlreiche
    0.09
     numerous
    0.09
     inúmer
    0.09
     বহু
    0.09
     rapper
    0.09
    Activations Density 0.003%

    No Known Activations