© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 63344
    Prev
    Next
    INDEX
    Explanations

    neck

    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
    ounen
    -0.08
    वाद
    -0.08
    ("/{
    -0.08
     quasi
    -0.08
    бир
    -0.08
     ga
    -0.07
    ，↵
    -0.07
     brood
    -0.07
     frac
    -0.07
    征
    -0.07
    POSITIVE LOGITS
    0.08
    関連
    0.08
    -ম
    0.08
    Pode
    0.08
    -dot
    0.07
     సర
    0.07
    ▄
    0.07
    ানি
    0.07
    -ה
    0.07
    -inspired
    0.07
    Activations Density 0.008%
    No Known Activations