© 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. 79042
    Prev
    Next
    INDEX
    Explanations

    summaries

    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
     uh
    -0.08
     onafh
    -0.07
     daarvoor
    -0.07
    Only
    -0.07
    ?).
    -0.07
    HIR
    -0.07
    Normal
    -0.07
     atun
    -0.07
     hore
    -0.07
    \r
    -0.07
    POSITIVE LOGITS
     thoughtfully
    0.09
     вполне
    0.09
     remarkably
    0.09
     אלו
    0.09
     Nad
    0.09
     என்பது
    0.09
    之家
    0.08
     הללו
    0.08
    удың
    0.08
     czyn
    0.08
    Activations Density 0.074%

    No Known Activations