© 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. 24585
    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
     ming
    -0.10
     invented
    -0.09
     scam
    -0.08
     scams
    -0.08
     mashed
    -0.08
     moje
    -0.08
    雀
    -0.08
     mango
    -0.08
     approvals
    -0.08
    جهه
    -0.08
    POSITIVE LOGITS
     corrobor
    0.13
     investigated
    0.10
     investigate
    0.10
     findings
    0.09
     investigates
    0.09
     Conclusions
    0.09
     investigating
    0.09
    ......
    0.09
     Findings
    0.09
    ˆ
    0.09
    Activations Density 0.035%

    No Known Activations