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. 88124
    Prev
    Next
    INDEX
    Explanations

    result

    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
    بود
    -0.08
    cite
    -0.08
    holds
    -0.08
    েহ
    -0.07
    oche
    -0.07
     Leads
    -0.07
    inf
    -0.07
     хватает
    -0.07
    ин
    -0.07
    anned
    -0.07
    POSITIVE LOGITS
    Pretty
    0.09
     formatted
    0.09
    出来
    0.09
    Formatted
    0.09
     prominently
    0.08
     Pretty
    0.08
     بطريقة
    0.08
     출력
    0.07
     prett
    0.07
     anzeigen
    0.07
    Activations Density 0.022%

    No Known Activations