© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95271
    Prev
    Next
    INDEX
    Explanations

    schedule

    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
     aggregator
    -0.08
     Aggreg
    -0.07
     winning
    -0.07
    aggreg
    -0.07
    wide
    -0.07
     �
    -0.07
     frat
    -0.07
     massiv
    -0.07
    wall
    -0.07
     molten
    -0.07
    POSITIVE LOGITS
     профилакти
    0.15
     regelmäß
    0.14
     preventive
    0.14
     регуляр
    0.13
     yearly
    0.13
     annuelle
    0.13
     prophyl
    0.13
     preventative
    0.13
     دوري
    0.13
     नियमित
    0.13
    Activations Density 0.031%

    No Known Activations