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. 52787
    Prev
    Next
    INDEX
    Explanations

    predictive coding

    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
     CIM
    -0.08
     Oracle
    -0.08
    Datatype
    -0.08
     numeric
    -0.07
     사항
    -0.07
    Numeric
    -0.07
     word
    -0.07
    igar
    -0.07
    Fleet
    -0.07
    Dat
    -0.07
    POSITIVE LOGITS
     predictions
    0.09
     axios
    0.08
     voorsp
    0.08
     முய
    0.08
     striving
    0.08
     predicts
    0.08
     xuyên
    0.08
     predictive
    0.08
     betalen
    0.08
     muñ
    0.08
    Activations Density 0.003%

    No Known Activations