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. 11-RESID-POST-AA
    6. 44143
    Prev
    Next
    INDEX
    Explanations

    disagreement or contradiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     విన
    -0.08
     Butterfly
    -0.08
    Checkpoint
    -0.08
     ব্যবহার
    -0.08
    umo
    -0.08
     importantly
    -0.07
    =user
    -0.07
    _batches
    -0.07
     Hits
    -0.07
     OPS
    -0.07
    POSITIVE LOGITS
    unlikely
    0.09
    definitions
    0.08
     unforeseen
    0.08
     unexpectedly
    0.08
     rul
    0.08
    たり
    0.08
     intval
    0.08
     inadvert
    0.08
     inadvertently
    0.08
     unclear
    0.08
    Activations Density 0.051%

    No Known Activations