© 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. 68069
    Prev
    Next
    INDEX
    Explanations

    leetspeak

    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
     Beds
    -0.09
     sumi
    -0.09
    Usr
    -0.09
     زمینه
    -0.09
    edd
    -0.08
     Trom
    -0.08
    etti
    -0.08
     Zoll
    -0.08
     Yangon
    -0.08
     Kommune
    -0.08
    POSITIVE LOGITS
     cheer
    0.08
    nost
    0.07
     partir
    0.07
    uropa
    0.07
     RUN
    0.07
    мож
    0.07
     ನಿಮ
    0.07
    iphers
    0.07
    isyen
    0.07
     ran
    0.07
    Activations Density 0.018%

    No Known Activations