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. 58583
    Prev
    Next
    INDEX
    Explanations

    censor

    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
     pavement
    -0.08
    oger
    -0.08
     Fibonacci
    -0.07
     geheel
    -0.07
     Sitz
    -0.07
     concrete
    -0.07
    ocyte
    -0.07
     Supremo
    -0.07
     Napoleon
    -0.07
     Schro
    -0.07
    POSITIVE LOGITS
    删
    0.10
     censorship
    0.10
     cens
    0.10
     censor
    0.10
     profanity
    0.09
     omissions
    0.09
     версии
    0.08
    /version
    0.08
    _ED
    0.08
     edgy
    0.08
    Activations Density 0.009%

    No Known Activations