© 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. 11-RESID-POST-AA
    11. 45765
    Prev
    Next
    INDEX
    Explanations

    file paths, local

    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
    velo
    -0.08
     Luz
    -0.08
     rec
    -0.07
    725
    -0.07
     ovom
    -0.07
     preth
    -0.07
    ynchronize
    -0.07
     firstly
    -0.07
    Tecn
    -0.07
     eigenlijk
    -0.07
    POSITIVE LOGITS
    стік
    0.08
     विष
    0.08
     catalysts
    0.08
    untungan
    0.08
    ාව
    0.08
    시키
    0.08
     beurs
    0.08
     catalyst
    0.08
    덤
    0.08
    افر
    0.08
    Activations Density 0.000%

    No Known Activations