© 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. 20796
    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
    ed
    -0.10
    edan
    -0.09
    ords
    -0.09
    akao
    -0.09
    idan
    -0.09
    ing
    -0.09
    oids
    -0.08
    antly
    -0.08
    uated
    -0.08
    uctor
    -0.08
    POSITIVE LOGITS
    ology
    0.11
    LOGY
    0.11
    ologies
    0.11
     adopted
    0.11
     approach
    0.11
     approaches
    0.10
    ological
    0.10
     aspects
    0.10
     rigor
    0.10
     दृष्ट
    0.10
    Activations Density 0.008%

    No Known Activations