© 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 EvalsExportsinterp-engineNEWAPI 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. 63224
    Prev
    Next
    INDEX
    Explanations

    yes

    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
     دھ
    -0.07
    kamers
    -0.07
     pistas
    -0.07
    (Is
    -0.07
    パン
    -0.07
     اچ
    -0.07
     KD
    -0.07
     solitary
    -0.07
    trate
    -0.07
    De
    -0.07
    POSITIVE LOGITS
    하면
    0.11
    െങ്കിൽ
    0.09
    的话
    0.08
    이면
    0.08
     হলে
    0.08
     असल्य
    0.08
     gb
    0.08
    ితే
    0.08
    ，可以
    0.08
     tev
    0.08
    Activations Density 0.045%

    No Known Activations