© 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. 11-RESID-POST-AA
    6. 25899
    Prev
    Next
    INDEX
    Explanations

    safety and caution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (?,
    -0.08
    wf
    -0.08
    Fib
    -0.07
    ético
    -0.07
    NF
    -0.07
    -0.07
    Nt
    -0.07
     집
    -0.07
    T
    -0.07
    assemble
    -0.07
    POSITIVE LOGITS
     precaution
    0.14
     proactively
    0.12
     precaut
    0.11
     prophyl
    0.11
     comunque
    0.10
     proactive
    0.10
     precautions
    0.10
     recomand
    0.10
     рекомендуется
    0.10
     anyways
    0.10
    Activations Density 0.093%

    No Known Activations