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. 337
    Prev
    Next
    INDEX
    Explanations

    Neural network dependencies

    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
     Practices
    -0.10
     Vorge
    -0.09
     Procedures
    -0.09
     Lamps
    -0.09
     procedimientos
    -0.08
     Practice
    -0.08
     fled
    -0.08
     Procedure
    -0.08
    illage
    -0.08
     Software
    -0.08
    POSITIVE LOGITS
     capturing
    0.12
     captured
    0.12
    capt
    0.11
     capture
    0.10
    Capt
    0.10
     temporal
    0.10
     correlations
    0.10
    捕
    0.09
    Temporal
    0.09
     captures
    0.09
    Activations Density 0.008%

    No Known Activations