© 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. 15-RESID-POST-AA
    6. 16510
    Prev
    Next
    INDEX
    Explanations

    ereal

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     savvy
    -0.08
    ekh
    -0.07
     SEX
    -0.07
    history
    -0.07
    History
    -0.07
    Cov
    -0.07
     특정
    -0.07
     Open
    -0.07
    obin
    -0.07
    Open
    -0.07
    POSITIVE LOGITS
     분위
    0.15
     dreamy
    0.13
     Atmosphäre
    0.12
     атмосфер
    0.12
     atmosfer
    0.11
     atmosfera
    0.11
     ambiance
    0.11
     atmosphere
    0.11
     atmos
    0.11
    �
    0.10
    Activations Density 0.005%

    No Known Activations