© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103052
    Prev
    Next
    INDEX
    Explanations

    Tokenizer

    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
     filif
    -0.10
    ged
    -0.09
    anson
    -0.09
    letjes
    -0.09
     sanitaire
    -0.08
    asley
    -0.08
     tíð
    -0.08
    enson
    -0.08
    asan
    -0.08
    әргә
    -0.08
    POSITIVE LOGITS
    करण
    0.08
    .encode
    0.08
    器
    0.07
    训练
    0.07
    VERSE
    0.07
    -go
    0.07
    (serializers
    0.07
    יניים
    0.07
     tâm
    0.07
     khí
    0.07
    Activations Density 0.003%

    No Known Activations