© 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. 18909
    Prev
    Next
    INDEX
    Explanations

    say "the ending -istant"

    np_max-act-logits · gemini-2.0-flash
    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
    Diagonal
    -0.08
    This
    -0.08
     이것
    -0.08
    ...”
    -0.08
    응
    -0.08
    Northern
    -0.07
     this
    -0.07
     이러한
    -0.07
    ...
    -0.07
    Further
    -0.07
    POSITIVE LOGITS
     Berikut
    0.09
    ýeti
    0.09
     birnäçe
    0.09
     jaroj
    0.09
    igeze
    0.09
     dürli
    0.09
    分pk
    0.09
    ýär
    0.09
     చే�
    0.09
     ៖
    0.09
    Activations Density 0.073%

    No Known Activations