© 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. 21539
    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
    <|reserved_200011|>
    -0.12
    /Subthreshold
    -0.12
    /fwlink
    -0.10
    …but
    -0.10
    彩堂
    -0.10
    &returns
    -0.10
    зык
    -0.10
    /Foundation
    -0.10
    ↵↵　↵
    -0.10
    /her
    -0.10
    POSITIVE LOGITS
     an
    0.16
     some
    0.15
     these
    0.15
     the
    0.14
     various
    0.14
     another
    0.14
     a
    0.14
     any
    0.13
     different
    0.13
     this
    0.13
    Activations Density 0.152%

    No Known Activations