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. 11688
    Prev
    Next
    INDEX
    Explanations

    Bus/signal priority

    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
     output
    -0.09
     incorrectly
    -0.08
     dict
    -0.08
    .output
    -0.08
    (output
    -0.08
    -output
    -0.08
     surn
    -0.07
     год
    -0.07
    934
    -0.07
    േഴ
    -0.07
    POSITIVE LOGITS
     privileged
    0.13
     privileges
    0.11
     privil
    0.11
     privilege
    0.11
    Privileges
    0.10
     dedicate
    0.10
     dedicated
    0.10
     Priv
    0.10
    Dedicated
    0.10
     Dedicated
    0.10
    Activations Density 0.034%

    No Known Activations