© 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. 78289
    Prev
    Next
    INDEX
    Explanations

    engineering textbooks

    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
     написал
    -0.09
     Linux
    -0.08
     voici
    -0.08
     krem
    -0.08
     wrote
    -0.08
     escribe
    -0.08
     Microsoft
    -0.07
     ****************************************************************
    -0.07
    еҳ
    -0.07
     ilman
    -0.07
    POSITIVE LOGITS
    chy
    0.08
    och
    0.08
    alleled
    0.08
    hep
    0.08
    hema
    0.08
    normally
    0.08
    gon
    0.08
    ovi
    0.08
    ्न
    0.08
    brite
    0.08
    Activations Density 0.000%

    No Known Activations