© 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. 23-RESID-POST-AA
    11. 51004
    Prev
    Next
    INDEX
    Explanations

    say "through"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     કદ
    -0.08
    okot
    -0.08
    %",↵
    -0.07
     ordinal
    -0.07
     ništa
    -0.07
     angeb
    -0.07
    %">↵
    -0.07
    %"↵
    -0.07
     ?.
    -0.07
     নেই
    -0.07
    POSITIVE LOGITS
     though
    0.31
    Though
    0.21
     Though
    0.21
    though
    0.21
    _th
    0.20
     thor
    0.20
     trough
    0.19
     th
    0.17
    -th
    0.16
     aunque
    0.16
    Activations Density 0.056%

    No Known Activations