© 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. 23-RESID-POST-AA
    11. 5409
    Prev
    Next
    INDEX
    Explanations

    Foreign words for "help"

    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
    לט
    -0.08
    geteilt
    -0.08
    .To
    -0.08
    बस
    -0.08
    zugehen
    -0.07
    weke
    -0.07
     saanud
    -0.07
    -char
    -0.07
    ilt
    -0.07
     जाकर
    -0.07
    POSITIVE LOGITS
     beitragen
    0.12
     کمک
    0.12
     führen
    0.10
     führt
    0.10
     ന
    0.09
     ختم
    0.09
     anh
    0.09
     yordam
    0.09
     katk
    0.09
     beitr
    0.09
    Activations Density 0.002%

    No Known Activations