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. 42151
    Prev
    Next
    INDEX
    Explanations

    rebuttals, arguments

    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
    ital
    -0.08
    .options
    -0.07
     whim
    -0.07
    obilier
    -0.07
     conventions
    -0.07
    ique
    -0.07
    iete
    -0.07
    ocl
    -0.07
    ોલ
    -0.07
    .vars
    -0.07
    POSITIVE LOGITS
    真正
    0.11
     여부
    0.10
     truly
    0.10
     Truly
    0.10
     réellement
    0.09
     Contrary
    0.09
     daadwerkelijk
    0.09
     myths
    0.09
     Myth
    0.09
     conclus
    0.09
    Activations Density 0.126%

    No Known Activations