© 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. 539
    Prev
    Next
    INDEX
    Explanations

    lead poisoning

    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
     Dank
    -0.08
     உயிர
    -0.07
    �
    -0.07
    ெய
    -0.07
     Saunders
    -0.07
    =batch
    -0.07
     denote
    -0.07
     Separator
    -0.07
    いただ
    -0.07
     வேண்ட
    -0.07
    POSITIVE LOGITS
     IPV
    0.08
     fathers
    0.08
     famously
    0.08
     ويل
    0.08
    DOM
    0.08
     истор
    0.08
    _Core
    0.08
     huizen
    0.08
    _DOM
    0.08
    .CODE
    0.08
    Activations Density 0.008%

    No Known Activations