© 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. 3-RESID-POST-AA
    11. 13210
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stirring
    -0.09
     꾸
    -0.08
    ổ
    -0.08
     voix
    -0.08
     بل
    -0.07
     suc
    -0.07
    crud
    -0.07
     vn
    -0.07
     amph
    -0.07
     Faith
    -0.07
    POSITIVE LOGITS
    掉
    0.08
     Zodiac
    0.08
     disclaim
    0.07
    ेस
    0.07
     temptation
    0.07
    cracker
    0.07
    eras
    0.07
    திர
    0.07
     Shark
    0.07
    газ
    0.07
    Activations Density 0.009%

    No Known Activations