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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1473
    Prev
    Next
    INDEX
    Explanations

    ingredient measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     taba
    -0.08
    �
    -0.08
     मशीन
    -0.08
    机器
    -0.07
    卒
    -0.07
     CLA
    -0.07
     Hacks
    -0.07
     इस्त
    -0.07
    菲
    -0.07
    拳
    -0.07
    POSITIVE LOGITS
     proliferation
    0.09
     copper
    0.09
     Copper
    0.08
     Southampton
    0.07
    <<"
    0.07
    γχ
    0.07
     【
    0.07
    Actualizar
    0.07
     because
    0.07
     nuclear
    0.07
    Activations Density 0.000%

    No Known Activations