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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19142
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -0.10
     oder
    -0.08
     checking
    -0.08
    aud
    -0.07
    /s
    -0.07
     किंवा
    -0.07
    Checking
    -0.07
     Aud
    -0.07
    /g
    -0.07
     auditing
    -0.07
    POSITIVE LOGITS
     соответственно
    0.10
     бөгөөд
    0.10
     Typically
    0.10
     региона
    0.10
    通常
    0.09
     находится
    0.09
     обычно
    0.09
     consequently
    0.09
     Consequently
    0.09
     болып
    0.09
    Activations Density 0.063%

    No Known Activations