Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 113852
    Prev
    Next
    INDEX
    Explanations

    Gutenberg's printing press

    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
    -0.08
     haig
    -0.08
    hoso
    -0.08
    ках
    -0.07
    īt
    -0.07
     saint
    -0.07
     से
    -0.07
     məs
    -0.07
     прям
    -0.07
    refix
    -0.07
    POSITIVE LOGITS
     radically
    0.09
     breakthroughs
    0.08
     anunciar
    0.08
     anunci
    0.08
     لأول
    0.08
    ensdag
    0.08
     famously
    0.08
     בשנת
    0.07
    ندرية
    0.07
     Chicago
    0.07
    Activations Density 0.022%

    No Known Activations