© 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. 47371
    Prev
    Next
    INDEX
    Explanations

    --

    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
     धो
    -0.08
    CString
    -0.08
     ára
    -0.08
    continence
    -0.07
     Textile
    -0.07
    ening
    -0.07
     yak
    -0.07
     hydrocar
    -0.07
    iconduct
    -0.07
     prosper
    -0.07
    POSITIVE LOGITS
     author
    0.07
    Bench
    0.07
     dito
    0.07
     meant
    0.07
     sne
    0.07
     വ്യക്തമ
    0.07
     Wor
    0.07
     heading
    0.07
     сверху
    0.07
    icer
    0.07
    Activations Density 0.006%

    No Known Activations