© 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. 103297
    Prev
    Next
    INDEX
    Explanations

    say "there"

    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
     उसका
    -0.10
     seine
    -0.09
     जिसे
    -0.09
    anything
    -0.08
     उसकी
    -0.08
     dessen
    -0.08
     kanyang
    -0.08
     jeho
    -0.08
     individual's
    -0.08
    whose
    -0.08
    POSITIVE LOGITS
     there
    0.25
    There
    0.23
     There
    0.22
    "There
    0.20
     هناك
    0.20
    هناك
    0.19
     يوجد
    0.18
     υπάρχουν
    0.18
     terdapat
    0.17
    there
    0.17
    Activations Density 0.078%

    No Known Activations