© 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. 22454
    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
     некотор
    -0.11
     něco
    -0.10
     jotain
    -0.10
     näch
    -0.10
     République
    -0.10
     nekaj
    -0.10
     coś
    -0.09
     ankaŭ
    -0.09
     nešto
    -0.09
     nél
    -0.09
    POSITIVE LOGITS
     are
    0.17
     of
    0.15
     were
    0.12
    conomic
    0.11
     have
    0.11
    och
    0.11
     exist
    0.10
    ettings
    0.10
     whatsoever
    0.10
    et
    0.10
    Activations Density 0.005%

    No Known Activations