© 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. 78284
    Prev
    Next
    INDEX
    Explanations

    cardboard

    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
    agree
    -0.08
    =query
    -0.07
     kise
    -0.07
    Ell
    -0.07
     aka
    -0.07
     ไป
    -0.07
     Lus
    -0.07
     consist
    -0.07
    MIS
    -0.07
     Kam
    -0.07
    POSITIVE LOGITS
    芽
    0.09
    288
    0.09
     cellulose
    0.08
    Optimal
    0.08
     dioxide
    0.07
    �
    0.07
     pension
    0.07
     quickest
    0.07
     Prost
    0.07
    山县
    0.07
    Activations Density 0.002%

    No Known Activations