© 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. 15-RESID-POST-AA
    11. 16602
    Prev
    Next
    INDEX
    Explanations

    weak

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hurt
    -0.08
     огромное
    -0.08
    qin
    -0.07
     Babies
    -0.07
     Lore
    -0.07
     Browse
    -0.07
     Integral
    -0.07
     ABB
    -0.07
    스크
    -0.07
     Workflow
    -0.07
    POSITIVE LOGITS
    -quality
    0.12
    /no
    0.11
     kalidad
    0.11
    弱
    0.11
     kvalite
    0.11
     weaker
    0.11
    -hearted
    0.11
    quality
    0.10
     inferior
    0.10
     workmanship
    0.10
    Activations Density 0.066%

    No Known Activations