© 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. 19-RESID-POST-AA
    11. 103514
    Prev
    Next
    INDEX
    Explanations

    rank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    厨房
    -0.09
     warehouse
    -0.08
     לעצ
    -0.08
     Side
    -0.08
    warehouse
    -0.08
     limpiar
    -0.08
     cleans
    -0.08
     יעד
    -0.08
     software
    -0.08
    未来
    -0.08
    POSITIVE LOGITS
     rank
    0.12
    .rank
    0.12
    (rank
    0.12
    rank
    0.11
    Ranks
    0.11
     ranks
    0.11
     Rank
    0.10
     rankings
    0.10
    _rank
    0.10
    Rank
    0.10
    Activations Density 0.008%

    No Known Activations