© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96454
    Prev
    Next
    INDEX
    Explanations

    quotations

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     necesitamos
    -0.12
    ,需要
    -0.12
     ανάγκ
    -0.11
    Need
    -0.11
     neces
    -0.11
     besoins
    -0.11
     precisamos
    -0.11
     We'd
    -0.11
     Need
    -0.10
     necesitan
    -0.10
    POSITIVE LOGITS
    Could
    0.14
     could
    0.14
     Searching
    0.14
     Could
    0.14
     searching
    0.14
     검색
    0.14
    .search
    0.14
    検索
    0.13
     WAIT
    0.13
     Wait
    0.13
    Activations Density 0.076%

    No Known Activations