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. 43808
    Prev
    Next
    INDEX
    Explanations

    Abbeys/Monasteries

    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
     exfol
    -0.08
    алоў
    -0.08
     Crowd
    -0.08
    Message
    -0.07
    λάχισ
    -0.07
    Emoji
    -0.07
     pedestrians
    -0.07
    ОД
    -0.07
    Coun
    -0.07
     exhaust
    -0.07
    POSITIVE LOGITS
     proteção
    0.09
     Genesis
    0.09
     protección
    0.09
     Protection
    0.08
     protection
    0.08
     Associated
    0.08
     monaster
    0.08
     Trinity
    0.08
     могла
    0.08
     eigene
    0.08
    Activations Density 0.010%

    No Known Activations