© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7897
    Prev
    Next
    INDEX
    Explanations

    Risk/quality control & processes

    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
    ンズ
    -0.08
    jör
    -0.08
     because
    -0.07
     thuận
    -0.07
    NH
    -0.07
    動
    -0.07
    激情
    -0.07
    966
    -0.07
     whisky
    -0.07
    648
    -0.07
    POSITIVE LOGITS
     fortunately
    0.10
     Fortunately
    0.09
     φό
    0.08
     उपाय
    0.08
     Carefully
    0.08
     dedicated
    0.08
     anyways
    0.08
     luckily
    0.08
     carefully
    0.08
     workaround
    0.08
    Activations Density 0.100%

    No Known Activations