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. 90257
    Prev
    Next
    INDEX
    Explanations

    column

    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
    priority
    -0.08
    ensis
    -0.07
    -machine
    -0.07
     influences
    -0.06
     impacts
    -0.06
    assets
    -0.06
    asser
    -0.06
     Concrete
    -0.06
    -0.06
    -ui
    -0.06
    POSITIVE LOGITS
     teka
    0.09
     동안
    0.09
     pastime
    0.09
     별
    0.08
     devol
    0.08
     Sonne
    0.08
     KW
    0.08
     الحوار
    0.08
     andamento
    0.08
     קצר
    0.08
    Activations Density 0.011%

    No Known Activations