© 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 EvalsExportsinterp-engineNEWAPI 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. 22120
    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
    -0.09
     거리
    -0.08
     achieving
    -0.08
    ágrafo
    -0.08
     spørg
    -0.08
    秘诀
    -0.08
    เด็ด
    -0.08
     વચ્ચે
    -0.08
     арас
    -0.07
     tackling
    -0.07
    POSITIVE LOGITS
     trivial
    0.13
     redundant
    0.13
     useless
    0.12
     weaker
    0.12
     which
    0.11
     useful
    0.11
     mostly
    0.11
     worthless
    0.11
     meaningless
    0.10
     mild
    0.10
    Activations Density 0.018%
    No Known Activations