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. 90163
    Prev
    Next
    INDEX
    Explanations

    two

    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
     controvers
    -0.09
     дополн
    -0.08
    Milli
    -0.08
    Costo
    -0.07
     సమావేశ
    -0.07
    Financial
    -0.07
     sul
    -0.07
    ENN
    -0.07
     Donation
    -0.07
    Pct
    -0.07
    POSITIVE LOGITS
    ucle
    0.09
    姑娘
    0.09
     يا
    0.08
     cuentos
    0.08
     ignite
    0.08
    女孩
    0.08
     Wellness
    0.08
     tib
    0.08
     thym
    0.08
    大师
    0.08
    Activations Density 0.005%

    No Known Activations