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. 60631
    Prev
    Next
    INDEX
    Explanations

    Central

    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
     режим
    -0.08
     режима
    -0.08
    িফ
    -0.07
     সম্পাদক
    -0.07
     editorial
    -0.07
    honi
    -0.07
     manuf
    -0.07
     resignation
    -0.07
     pocos
    -0.07
     হল
    -0.07
    POSITIVE LOGITS
     passieren
    0.09
    ��
    0.09
     Beans
    0.08
    ls
    0.08
     Gems
    0.08
     geheugen
    0.08
    erdas
    0.07
    nuts
    0.07
     circulated
    0.07
    .chain
    0.07
    Activations Density 0.006%

    No Known Activations