© 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. 19551
    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
     таго
    -0.10
     predsjed
    -0.10
     причинам
    -0.10
     yén
    -0.10
     kuti
    -0.10
     jalma
    -0.10
     אַז
    -0.10
     તાલુક
    -0.10
     եկ
    -0.10
     proseso
    -0.09
    POSITIVE LOGITS
     not
    0.24
    not
    0.21
    n't
    0.20
     only
    0.20
    only
    0.18
    _not
    0.17
    Only
    0.17
    _only
    0.16
    Not
    0.16
     Only
    0.15
    Activations Density 0.029%

    No Known Activations