© 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. 91333
    Prev
    Next
    INDEX
    Explanations

    contamination

    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
    armac
    -0.08
     Equal
    -0.08
    74
    -0.08
     igualdad
    -0.08
    76
    -0.08
     kerajaan
    -0.07
     بس
    -0.07
     الاخت
    -0.07
    75
    -0.07
     əsas
    -0.07
    POSITIVE LOGITS
     Fleming
    0.09
     ghost
    0.08
     contamination
    0.08
    ghost
    0.08
     Centr
    0.08
     contamin
    0.08
     Gloves
    0.08
     Ghost
    0.08
    IMP
    0.08
     leakage
    0.08
    Activations Density 0.001%

    No Known Activations