© 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. 709
    Prev
    Next
    INDEX
    Explanations

    legacy

    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
    TOP
    -0.08
     entice
    -0.08
     reassure
    -0.08
    POL
    -0.08
     fluff
    -0.08
    PCR
    -0.08
     dislike
    -0.08
     nueve
    -0.08
     pouch
    -0.08
     وتق
    -0.08
    POSITIVE LOGITS
     legado
    0.14
     Legacy
    0.12
     legacy
    0.12
    Legacy
    0.12
     영향
    0.11
    legacy
    0.10
    贡献
    0.10
     impactful
    0.10
    意义
    0.10
     contribution
    0.09
    Activations Density 0.037%

    No Known Activations