© 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. 95812
    Prev
    Next
    INDEX
    Explanations

    statistical likelihood

    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
     percussion
    -0.09
     JScroll
    -0.08
     Trending
    -0.08
    进口
    -0.08
     drills
    -0.08
     envisioned
    -0.08
     trendy
    -0.08
    配送
    -0.08
    Destination
    -0.08
     UIColor
    -0.08
    POSITIVE LOGITS
    Likelihood
    0.13
    ikelihood
    0.13
     likelihood
    0.12
     Bayesian
    0.12
    MLE
    0.10
    elihood
    0.10
    .argmax
    0.10
    entropy
    0.09
     Rosen
    0.09
     posterior
    0.09
    Activations Density 0.005%

    No Known Activations