© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47153
    Prev
    Next
    INDEX
    Explanations

    ABC analysis

    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
    満
    -0.09
     prerecorded
    -0.08
     meet
    -0.08
     stated
    -0.08
     Artemis
    -0.07
     meeting
    -0.07
    истан
    -0.07
    녀
    -0.07
     silic
    -0.07
     volto
    -0.07
    POSITIVE LOGITS
     annuelle
    0.09
     anual
    0.09
     CAGR
    0.09
    _analysis
    0.08
    _bins
    0.08
     регулярно
    0.08
    quets
    0.08
    Grouping
    0.08
     ежедневно
    0.08
    checksum
    0.08
    Activations Density 0.006%

    No Known Activations