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. 53267
    Prev
    Next
    INDEX
    Explanations

    literary themes

    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
     แจ
    -0.09
     Cached
    -0.08
     angenehm
    -0.08
     Verte
    -0.08
     tack
    -0.08
     Rank
    -0.08
     intégré
    -0.08
     Cone
    -0.08
     cone
    -0.08
     Dankzij
    -0.08
    POSITIVE LOGITS
     portrayed
    0.10
     redemption
    0.09
     relentless
    0.09
     obsessive
    0.09
     bitters
    0.09
     striving
    0.09
     रिश्त
    0.09
     strives
    0.09
     humanity
    0.09
     longing
    0.09
    Activations Density 0.119%

    No Known Activations