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. 56269
    Prev
    Next
    INDEX
    Explanations

    money laundering

    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
     promptly
    -0.09
     swiftly
    -0.08
    \Abstract
    -0.08
    .PERM
    -0.08
    pless
    -0.08
    .null
    -0.08
     Predict
    -0.07
    -0.07
    _attribute
    -0.07
    ison
    -0.07
    POSITIVE LOGITS
     afkomstig
    0.11
     provenientes
    0.08
     berasal
    0.08
     yoz
    0.08
     įvair
    0.08
     берген
    0.08
    레이
    0.08
     purification
    0.08
     myths
    0.08
     түс
    0.08
    Activations Density 0.010%

    No Known Activations