© 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. 11-RESID-POST-AA
    11. 75631
    Prev
    Next
    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    му
    -0.08
     monst
    -0.08
    <m
    -0.08
     лад
    -0.08
     기
    -0.08
     leisurely
    -0.08
     الأمور
    -0.08
     kannst
    -0.08
    企
    -0.08
    だ
    -0.08
    POSITIVE LOGITS
     examined
    0.13
     surveyed
    0.11
     respondents
    0.11
     examining
    0.10
     interviewed
    0.10
     sampled
    0.10
     undergoing
    0.10
     questionnaires
    0.10
     sample
    0.10
     examine
    0.09
    Activations Density 0.106%

    No Known Activations