© 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. 102522
    Prev
    Next
    INDEX
    Explanations

    obscurity

    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
    _OTHER
    -0.09
    ILLA
    -0.09
     Prüfung
    -0.09
     سایر
    -0.08
     لأي
    -0.08
     checking
    -0.08
    तान
    -0.08
     പരിശോധ
    -0.08
     دیگر
    -0.08
     prüfen
    -0.08
    POSITIVE LOGITS
     obsc
    0.11
     obscure
    0.11
     अस्प
    0.11
     भ्रम
    0.10
     ambiguous
    0.10
     opaque
    0.10
     ignorance
    0.10
     fog
    0.09
     confund
    0.09
     misunderstanding
    0.09
    Activations Density 0.225%

    No Known Activations