© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 103183
    Prev
    Next
    INDEX
    Explanations

    say "these" or "those"

    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
     हा
    -0.11
    _this
    -0.11
    This
    -0.09
     ਇਸ
    -0.09
     որը
    -0.09
    हा
    -0.09
     This
    -0.09
    Questo
    -0.08
     ovaj
    -0.08
    ционный
    -0.08
    POSITIVE LOGITS
     these
    0.64
     These
    0.58
    These
    0.57
    这些
    0.57
    these
    0.56
     этих
    0.50
     estos
    0.47
     essas
    0.47
     queste
    0.46
     aquestes
    0.45
    Activations Density 2.259%

    No Known Activations