Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19502
    Prev
    Next
    INDEX
    Explanations

    Math

    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
     最新
    -0.08
     تاز
    -0.08
    518
    -0.08
     Apenas
    -0.08
     freshest
    -0.07
    ”!
    -0.07
    ANTITY
    -0.07
     freshness
    -0.07
     свеж
    -0.07
     essência
    -0.07
    POSITIVE LOGITS
     (§
    0.10
    	for
    0.10
    하거나
    0.08
     (`
    0.08
    kari
    0.08
    tnings
    0.08
    lite
    0.08
    jj
    0.08
    Watch
    0.08
     regex
    0.08
    Activations Density 0.028%

    No Known Activations