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. 12134
    Prev
    Next
    INDEX
    Explanations

    this

    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
     oper
    -0.08
     poz
    -0.08
    -ang
    -0.07
    723
    -0.07
    ное
    -0.07
    签到
    -0.07
    記事
    -0.07
     αυτή
    -0.07
    ____________
    -0.07
     तरी
    -0.06
    POSITIVE LOGITS
     nedenle
    0.09
    意味着
    0.09
    järel
    0.08
    时候
    0.08
    .gb
    0.08
    've
    0.08
     Bailey
    0.08
     �
    0.08
     Roch
    0.08
     పొ
    0.08
    Activations Density 0.300%

    No Known Activations