© 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. 23-RESID-POST-AA
    11. 96592
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Steele
    -0.08
     Les
    -0.07
    fet
    -0.07
     adhes
    -0.07
    FE
    -0.07
    Helmet
    -0.07
    Neighbors
    -0.07
    helmet
    -0.07
    fe
    -0.07
     led
    -0.07
    POSITIVE LOGITS
    旦
    0.09
    сяг
    0.09
    而言
    0.08
    eraard
    0.08
    当然
    0.08
    өөс
    0.08
     lle
    0.08
    ètes
    0.08
    552
    0.08
    арып
    0.08
    Activations Density 0.000%

    No Known Activations