© 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. 103289
    Prev
    Next
    INDEX
    Explanations

    :

    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
     mesurer
    -0.08
     fills
    -0.07
     knows
    -0.07
     liten
    -0.07
     closes
    -0.07
    …………
    -0.07
    inaire
    -0.07
     pequeña
    -0.07
     for
    -0.07
    …↵↵
    -0.06
    POSITIVE LOGITS
     `$
    0.13
     "$
    0.12
     "**
    0.11
     $$
    0.11
     "$(
    0.10
     $\
    0.10
    جات
    0.10
     _$
    0.10
     "{$
    0.10
     rewritten
    0.10
    Activations Density 0.037%

    No Known Activations