Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90185
    Prev
    Next
    INDEX
    Explanations

    4

    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
     novelty
    -0.09
     cláss
    -0.08
     decor
    -0.08
     美
    -0.08
     observar
    -0.08
    Classic
    -0.08
     classics
    -0.08
    ymy
    -0.08
    Mixin
    -0.08
     classique
    -0.08
    POSITIVE LOGITS
     Faktoren
    0.08
     Kommune
    0.08
     teams
    0.07
     عوامل
    0.07
    /logo
    0.07
     Iss
    0.07
    發
    0.07
     Surge
    0.07
     команда
    0.07
     تیم
    0.07
    Activations Density 0.001%

    No Known Activations