© 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. 30908
    Prev
    Next
    INDEX
    Explanations

    ticket

    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
     clocks
    -0.09
     Dhabi
    -0.09
     permiss
    -0.08
     cautiously
    -0.08
     ketogenic
    -0.08
     products
    -0.08
     selectively
    -0.08
     силу
    -0.08
     ETFs
    -0.08
    esson
    -0.08
    POSITIVE LOGITS
    投诉
    0.16
     complaints
    0.13
    Complaint
    0.13
     অভিযোগ
    0.12
     ફરિયાદ
    0.12
     tiket
    0.12
     शिकायत
    0.12
     Complaint
    0.11
     complaint
    0.11
     പരാതി
    0.11
    Activations Density 0.062%

    No Known Activations