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. 88221
    Prev
    Next
    INDEX
    Explanations

    Na

    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
    mus
    -0.10
     leader
    -0.08
     Mus
    -0.08
    多人
    -0.08
     नेता
    -0.07
     Artificial
    -0.07
     Leader
    -0.07
     floors
    -0.07
     Multip
    -0.07
    ultiple
    -0.07
    POSITIVE LOGITS
    徳
    0.08
    زيد
    0.08
     જાય
    0.08
     совмест
    0.08
    елябин
    0.08
    իլի
    0.08
     burde
    0.08
    @Join
    0.08
    취
    0.08
    իլիոն
    0.08
    Activations Density 0.002%

    No Known Activations