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. 11-RESID-POST-AA
    6. 53985
    Prev
    Next
    INDEX
    Explanations

    sets

    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
    ર્ગ
    -0.08
    zyk
    -0.08
     agitation
    -0.08
    akin
    -0.07
    ૂર
    -0.07
    ەر
    -0.07
    -0.07
     deliver
    -0.07
    adrat
    -0.07
     mediation
    -0.07
    POSITIVE LOGITS
     আরও
    0.09
     boste
    0.08
     Rubber
    0.08
     Quantity
    0.08
    :+
    0.07
    Sku
    0.07
     Anonymous
    0.07
    ANE
    0.07
    Blocks
    0.07
    Fax
    0.07
    Activations Density 0.000%

    No Known Activations