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. 113050
    Prev
    Next
    INDEX
    Explanations

    ichi

    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
    -h
    -0.08
    _rem
    -0.08
     jailbreak
    -0.08
     Тем
    -0.08
    yre
    -0.07
    710
    -0.07
    opl
    -0.07
    /mobile
    -0.07
     ハ
    -0.07
    -ban
    -0.07
    POSITIVE LOGITS
     textbook
    0.08
     chemically
    0.08
     inorganic
    0.08
    事項
    0.08
     favorable
    0.08
     অনুয
    0.08
    গত
    0.07
    偿
    0.07
     simb
    0.07
    량
    0.07
    Activations Density 0.002%

    No Known Activations