© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65481
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    ieron
    -0.08
     cortic
    -0.08
    _linux
    -0.08
     princípio
    -0.08
    ,很
    -0.07
    顔
    -0.07
    �
    -0.07
    నే
    -0.07
    persona
    -0.07
    Fullscreen
    -0.07
    POSITIVE LOGITS
    из
    0.08
     ríg
    0.08
     redundant
    0.07
    $$
    0.07
     Rehabilitation
    0.07
     bulls
    0.07
    mäß
    0.07
     quoi
    0.07
     Renewal
    0.07
     мак
    0.07
    Activations Density 0.191%

    No Known Activations