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. 77410
    Prev
    Next
    INDEX
    Explanations

    mathematical differences/distances

    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
     ALG
    -0.08
     fermer
    -0.08
    -0.08
     NBC
    -0.08
    fc
    -0.07
     Agua
    -0.07
    Fed
    -0.07
     Fc
    -0.07
     alum
    -0.07
    FTC
    -0.07
    POSITIVE LOGITS
     दूरी
    0.09
     расстоя
    0.09
     shortcuts
    0.09
    _DIFF
    0.09
    -distance
    0.08
     hatred
    0.08
    úst
    0.08
     comprimento
    0.08
    Diff
    0.08
     distances
    0.08
    Activations Density 0.019%

    No Known Activations