© 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. 15-RESID-POST-AA
    11. 16300
    Prev
    Next
    INDEX
    Explanations

    consensus

    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
     उल
    -0.07
    entic
    -0.07
     balconies
    -0.07
     под
    -0.07
     übertragen
    -0.07
    orie
    -0.07
    layan
    -0.07
    (register
    -0.07
    (lat
    -0.07
    (seconds
    -0.07
    POSITIVE LOGITS
     consensus
    0.17
     Consensus
    0.15
     consenso
    0.15
    Consensus
    0.14
     بشأن
    0.14
     حول
    0.14
     agreement
    0.13
    认为
    0.12
     agreeing
    0.11
    Agreement
    0.11
    Activations Density 0.011%

    No Known Activations