© 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. 19-RESID-POST-AA
    11. 20568
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _names
    -0.09
     одну
    -0.08
     가능한
    -0.08
     гэтыя
    -0.08
     enige
    -0.08
     Names
    -0.08
     eneste
    -0.08
     बराब
    -0.08
     iedere
    -0.08
    .any
    -0.08
    POSITIVE LOGITS
    因素
    0.15
     factors
    0.14
     factoren
    0.14
     factores
    0.14
     Faktoren
    0.14
     عوامل
    0.13
     fatores
    0.12
     facteurs
    0.12
     Factors
    0.11
     факторов
    0.11
    Activations Density 0.014%

    No Known Activations