© 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. 102713
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    ушы
    -0.10
    çao
    -0.09
    ندوق
    -0.08
    -fluid
    -0.08
    چى
    -0.08
     çift
    -0.08
    شاب
    -0.08
    ujuss
    -0.08
    აკუთ
    -0.08
     მს
    -0.08
    POSITIVE LOGITS
     məlumat
    0.08
     utilisant
    0.08
     использования
    0.08
     yayin
    0.08
     responding
    0.07
     era
    0.07
     coloring
    0.07
     antwort
    0.07
     utilizar
    0.07
     utilizzare
    0.07
    Activations Density 0.000%

    No Known Activations