© 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. 22463
    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
    шее
    -0.10
     Danny
    -0.08
    pona
    -0.08
    кое
    -0.08
    شاب
    -0.08
    =this
    -0.08
    ambles
    -0.07
    悪
    -0.07
     strokes
    -0.07
     LINKS
    -0.07
    POSITIVE LOGITS
    _{
    0.24
    _base
    0.20
    �
    0.20
    _{\
    0.19
    _BASE
    0.17
     base
    0.17
    _
    0.16
    Base
    0.16
    _\
    0.16
    _Base
    0.16
    Activations Density 0.016%

    No Known Activations