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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7665
    Prev
    Next
    INDEX
    Explanations

    背景

    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
     Tyr
    -0.09
    アル
    -0.08
     Alec
    -0.08
     Ál
    -0.08
     tank
    -0.08
     tanque
    -0.08
     polyval
    -0.08
    -fer
    -0.07
    ******/↵
    -0.07
     Die
    -0.07
    POSITIVE LOGITS
     motivation
    0.11
     rationale
    0.11
     motivations
    0.11
     Motivation
    0.11
    Importance
    0.11
    Why
    0.10
     motivates
    0.10
     significance
    0.09
     motivate
    0.09
     motivating
    0.09
    Activations Density 0.018%

    No Known Activations