© 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. 47738
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Creating
    -0.11
    Creates
    -0.11
    (Create
    -0.10
     Erstellung
    -0.10
     Performing
    -0.10
    .Create
    -0.10
     Checking
    -0.10
     Create
    -0.10
    Analy
    -0.10
    Соз
    -0.10
    POSITIVE LOGITS
     find
    0.27
     найти
    0.23
     determine
    0.22
     encontrar
    0.21
    find
    0.21
     trouver
    0.20
     trovare
    0.20
    .find
    0.19
    找到
    0.19
     finne
    0.19
    Activations Density 0.187%

    No Known Activations