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. 77241
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    ən
    -0.08
     Kool
    -0.08
    eleri
    -0.08
    oude
    -0.08
    -----------
    -0.08
    Sher
    -0.08
     dirigido
    -0.08
    elassen
    -0.08
     מוח
    -0.07
    Wrong
    -0.07
    POSITIVE LOGITS
    �
    0.08
     thumb
    0.08
     прок
    0.08
    048
    0.08
     ‌
    0.07
    050
    0.07
    �
    0.07
     للط
    0.07
     Dazu
    0.07
     ajust
    0.07
    Activations Density 0.090%

    No Known Activations