© 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. 7-RESID-POST-AA
    11. 1336
    Prev
    Next
    INDEX
    Explanations

    PEG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     superiority
    -0.08
     Collar
    -0.08
     itk
    -0.08
     시험
    -0.08
    wah
    -0.08
    시험
    -0.08
     시행
    -0.08
     Chesapeake
    -0.08
     �
    -0.07
     Amy
    -0.07
    POSITIVE LOGITS
     disposition
    0.08
     convertible
    0.08
    regexp
    0.08
     freelance
    0.08
     downtime
    0.07
    0.07
     obten
    0.07
     gratuito
    0.07
     sino
    0.07
     dispoz
    0.07
    Activations Density 0.000%
    No Known Activations