© 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. 11-RESID-POST-AA
    11. 24782
    Prev
    Next
    INDEX
    Explanations

    Matrix/algebraic problems

    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
     renov
    -0.08
     sober
    -0.07
    ాలని
    -0.07
     chargers
    -0.07
    embang
    -0.07
     continually
    -0.07
     demos
    -0.07
     Zo
    -0.07
     urges
    -0.07
     continuously
    -0.07
    POSITIVE LOGITS
     സ്ഥാന
    0.09
    位置
    0.09
     HC
    0.08
    index
    0.08
    ouvre
    0.08
    indice
    0.08
     масло
    0.08
     matric
    0.08
     correspondente
    0.08
    当前位置
    0.08
    Activations Density 0.012%

    No Known Activations