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. 19063
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    ống
    -0.08
    assa
    -0.08
    acchar
    -0.07
    acam
    -0.07
    ).↵↵
    -0.07
     couche
    -0.07
    erville
    -0.07
    	bw
    -0.07
    _skin
    -0.07
     cono
    -0.07
    POSITIVE LOGITS
     got
    0.11
    输入
    0.11
     detected
    0.10
    Retrieved
    0.10
     recibido
    0.09
    Input
    0.09
     questionable
    0.09
    	got
    0.09
     Got
    0.09
    Got
    0.09
    Activations Density 0.001%

    No Known Activations