© 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. 21159
    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
    む
    -0.09
     ساتھ
    -0.09
     hace
    -0.09
    :.
    -0.09
    :
    -0.08
    :m
    -0.08
    'agit
    -0.08
     dingen
    -0.08
    つ
    -0.08
    :*
    -0.08
    POSITIVE LOGITS
    lhs
    0.09
     lhs
    0.08
     delitos
    0.08
     αποτέλεσμα
    0.08
     observe
    0.08
     revisit
    0.07
     feasibility
    0.07
     нәти
    0.07
     crop
    0.07
    outing
    0.07
    Activations Density 0.000%

    No Known Activations