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

    Neuronpedia

    Jacobian LensNEW
    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. 64014
    Prev
    Next
    INDEX
    Explanations

    reflections

    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
     Google
    -0.07
     approche
    -0.07
     callable
    -0.07
     relational
    -0.07
    nof
    -0.07
     Texture
    -0.06
     attendu
    -0.06
    划
    -0.06
     halen
    -0.06
     tolerated
    -0.06
    POSITIVE LOGITS
     afterwards
    0.11
     subsequently
    0.11
     afterward
    0.10
     thereafter
    0.10
    进一步
    0.10
    Wins
    0.09
    風吹
    0.09
     tahap
    0.09
     further
    0.09
    阶段
    0.09
    Activations Density 0.129%

    No Known Activations