© 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. 50769
    Prev
    Next
    INDEX
    Explanations

    say "as"

    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
     Acts
    -0.09
    作为
    -0.08
    ಣದಲ್ಲಿ
    -0.08
    এক
    -0.08
    ラックバック
    -0.08
    �ლ
    -0.08
    েনে
    -0.08
    ここ
    -0.08
    �ი
    -0.08
     നിന്നും
    -0.08
    POSITIVE LOGITS
     than
    0.18
     kuin
    0.17
     quanto
    0.15
     जित
    0.14
     όσο
    0.13
    _than
    0.11
     જેટ
    0.11
     as
    0.11
     que
    0.11
     wie
    0.11
    Activations Density 0.029%

    No Known Activations