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. 53902
    Prev
    Next
    INDEX
    Explanations

    url

    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
     Mk
    -0.07
     voies
    -0.07
    Mk
    -0.07
     ddat
    -0.07
    pty
    -0.07
     desgr
    -0.07
     errone
    -0.07
     relocation
    -0.07
     refroid
    -0.07
     eveneens
    -0.07
    POSITIVE LOGITS
    .URL
    0.10
     сайты
    0.09
     websites
    0.09
    -url
    0.08
     компаний
    0.08
     url
    0.08
     URL
    0.08
     Attempt
    0.08
    (URL
    0.08
     google
    0.08
    Activations Density 0.001%

    No Known Activations