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. 11831
    Prev
    Next
    INDEX
    Explanations

    和

    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
     Jenkins
    -0.09
    uais
    -0.08
     phoenix
    -0.08
    itated
    -0.08
    Phoenix
    -0.08
    ワ
    -0.08
    -comp
    -0.07
    lean
    -0.07
    ognito
    -0.07
     머신
    -0.07
    POSITIVE LOGITS
     uppercase
    0.08
     الآن
    0.07
     сих
    0.07
     دې
    0.07
     dotted
    0.07
     וצ
    0.07
    .eng
    0.07
     meira
    0.07
     greatly
    0.07
     хүр
    0.07
    Activations Density 0.003%

    No Known Activations