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. 60841
    Prev
    Next
    INDEX
    Explanations

    logic

    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
     доволь
    -0.09
     youthful
    -0.08
     chứng
    -0.08
    VERIFY
    -0.08
    _VERIFY
    -0.08
     warmth
    -0.08
     qan
    -0.08
     얻
    -0.08
     राहत
    -0.08
    .random
    -0.08
    POSITIVE LOGITS
    禁止
    0.13
     stric
    0.12
     prohibits
    0.12
     prohibited
    0.12
     prohibition
    0.12
     prohib
    0.11
     offenders
    0.10
     forbid
    0.10
     prevention
    0.10
     offenses
    0.10
    Activations Density 0.028%

    No Known Activations