© 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. 103604
    Prev
    Next
    INDEX
    Explanations

    Foreign language related words

    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
     is
    -0.11
    ());↵
    -0.08
    ()));↵
    -0.08
     was
    -0.08
     చేసింది
    -0.08
     it
    -0.08
     specific
    -0.07
     has
    -0.07
     that
    -0.07
     per
    -0.07
    POSITIVE LOGITS
    分别
    0.14
     باشند
    0.13
     എന്നീ
    0.12
     These
    0.12
     എന്നിവർ
    0.12
    、↵↵
    0.12
     Estas
    0.11
    These
    0.11
     respectively
    0.11
     Then
    0.11
    Activations Density 0.037%

    No Known Activations