© 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. 160
    Prev
    Next
    INDEX
    Explanations

    translateZ(0) code

    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
     Tear
    -0.08
    mint
    -0.07
     tear
    -0.07
     demo
    -0.07
     Terra
    -0.07
     contamos
    -0.07
     직접
    -0.07
     custody
    -0.07
     TRE
    -0.07
     markdown
    -0.07
    POSITIVE LOGITS
    ային
    0.09
    फोन
    0.08
     رجل
    0.08
    ovým
    0.08
    φαση
    0.08
    անձն
    0.08
    یوں
    0.08
    یان
    0.08
    Techn
    0.08
    արս
    0.08
    Activations Density 0.000%

    No Known Activations