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. 58670
    Prev
    Next
    INDEX
    Explanations

    Saturn

    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
     mae
    -0.08
    程度
    -0.08
    crip
    -0.08
    dır
    -0.07
     من
    -0.07
     মাধ্যম
    -0.07
    යට
    -0.07
     segment
    -0.07
     Flyers
    -0.07
    apter
    -0.07
    POSITIVE LOGITS
     Sagittarius
    0.10
     conjunct
    0.09
     exalt
    0.08
     cupid
    0.08
     Вен
    0.08
     Baut
    0.08
     orbit
    0.08
     ocupar
    0.08
     Howard
    0.08
     günstig
    0.08
    Activations Density 0.007%

    No Known Activations