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. 52951
    Prev
    Next
    INDEX
    Explanations

    Abstaining from something

    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
     존재
    -0.08
     Goo
    -0.08
     unordered
    -0.07
    assembled
    -0.07
    (fill
    -0.07
     interplay
    -0.07
     KI
    -0.07
     chunks
    -0.07
    ển
    -0.07
    -0.07
    POSITIVE LOGITS
     abst
    0.13
    禁
    0.13
     禁
    0.13
     stric
    0.12
    戒
    0.12
    禁止
    0.11
     prohibition
    0.11
     vow
    0.11
     Abst
    0.11
     отказаться
    0.11
    Activations Density 0.082%

    No Known Activations