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. 111778
    Prev
    Next
    INDEX
    Explanations

    company-related texts

    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
    டி
    -0.09
    rovers
    -0.08
     që
    -0.08
    pecia
    -0.08
    จริง
    -0.07
     tão
    -0.07
     surg
    -0.07
    edian
    -0.07
     বিভ
    -0.07
     plethora
    -0.07
    POSITIVE LOGITS
    wash
    0.07
     Sub
    0.07
    Sub
    0.07
    _SUB
    0.07
     Wash
    0.07
    ®.
    0.07
    .sub
    0.07
    .company
    0.07
    Wash
    0.07
     (:
    0.07
    Activations Density 0.207%

    No Known Activations