© 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. 68712
    Prev
    Next
    INDEX
    Explanations

    square

    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
    NEW
    -0.08
    -new
    -0.08
     Ona
    -0.08
     Providence
    -0.08
    -New
    -0.08
     sveta
    -0.07
     Basilica
    -0.07
    Ella
    -0.07
    RST
    -0.07
     மூலம்
    -0.07
    POSITIVE LOGITS
    -ish
    0.09
    _submission
    0.08
    -rate
    0.08
     grabs
    0.08
    াতা
    0.08
    _rate
    0.08
     telecommunications
    0.07
    تال
    0.07
     même
    0.07
    兑现
    0.07
    Activations Density 0.008%

    No Known Activations