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. 59173
    Prev
    Next
    INDEX
    Explanations

    transaction isolation

    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
     logistics
    -0.09
     nom
    -0.08
     �
    -0.08
     bon
    -0.08
     chance
    -0.08
     logística
    -0.08
     volley
    -0.08
     phone
    -0.07
    soc
    -0.07
    atsis
    -0.07
    POSITIVE LOGITS
    Isolation
    0.11
     Isolation
    0.11
     isolates
    0.11
     수준
    0.09
     isolation
    0.09
    .Concurrent
    0.09
    隔
    0.09
     Detached
    0.08
     Reader
    0.08
     isolamento
    0.08
    Activations Density 0.002%

    No Known Activations