© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 3145
    Prev
    Next
    INDEX
    Explanations

    -Or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _RE
    -0.08
     entsteht
    -0.07
     Clarence
    -0.07
    .gen
    -0.07
    FULL
    -0.07
     relatives
    -0.07
    buy
    -0.07
    670
    -0.07
    460
    -0.07
     Samples
    -0.07
    POSITIVE LOGITS
     lide
    0.08
     oscur
    0.08
     mens
    0.07
     locality
    0.07
     donker
    0.07
     ladd
    0.07
    Objet
    0.07
    asang
    0.07
     Miles
    0.07
    ماه
    0.07
    Activations Density 0.003%

    No Known Activations