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. 76146
    Prev
    Next
    INDEX
    Explanations

    being drunk

    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
     αρχ
    -0.08
    Spark
    -0.08
    套餐
    -0.08
    packages
    -0.08
     boycott
    -0.08
    зв
    -0.08
    _stack
    -0.07
    Presence
    -0.07
     Spark
    -0.07
     inom
    -0.07
    POSITIVE LOGITS
     halluc
    0.10
     wander
    0.09
     abilities
    0.09
     wandered
    0.09
     spontan
    0.08
     cognit
    0.08
    能力
    0.08
     wandering
    0.08
     regained
    0.08
     Wander
    0.07
    Activations Density 0.058%

    No Known Activations