© 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. 11-RESID-POST-AA
    11. 77941
    Prev
    Next
    INDEX
    Explanations

    measurements and ranges

    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
    nington
    -0.08
    elyn
    -0.08
     downhill
    -0.08
     Christus
    -0.07
     charity
    -0.07
     ACC
    -0.07
     Mich
    -0.07
     momentum
    -0.07
     mercy
    -0.07
    riott
    -0.07
    POSITIVE LOGITS
    范围
    0.13
     range
    0.11
     диапаз
    0.11
     পর্যন্ত
    0.11
     Range
    0.10
     వరకు
    0.10
     ranges
    0.10
     suport
    0.10
    Range
    0.10
     zakres
    0.10
    Activations Density 0.033%

    No Known Activations