© 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. 47693
    Prev
    Next
    INDEX
    Explanations

    agent

    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
     GPT
    -0.08
     Neto
    -0.08
     Neder
    -0.08
    Advertising
    -0.08
     descriptive
    -0.07
    UBL
    -0.07
     HDL
    -0.07
     폐
    -0.07
     záv
    -0.07
    Uvs
    -0.07
    POSITIVE LOGITS
     agent
    0.15
    _agent
    0.14
     Agent
    0.14
    -agent
    0.14
     агент
    0.13
    agent
    0.13
     agente
    0.13
    .agent
    0.13
    Agent
    0.13
    _AGENT
    0.13
    Activations Density 0.003%

    No Known Activations