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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 98629
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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
     होते
    -0.10
     करते
    -0.10
     होता
    -0.09
    ిస్తుంది
    -0.08
    ిస్తున్నారు
    -0.08
    arts
    -0.08
     করছেন
    -0.08
     должно
    -0.08
     کرتے
    -0.08
     етеді
    -0.08
    POSITIVE LOGITS
    нил
    0.09
    итал
    0.08
    َّ
    0.08
    неше
    0.08
    ни
    0.08
    ё
    0.08
    iód
    0.07
    كى
    0.07
    001
    0.07
     erhältlich
    0.07
    Activations Density 0.004%

    No Known Activations