© 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. 129568
    Prev
    Next
    INDEX
    Explanations

    Berlin

    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
    鏈
    -0.08
    olan
    -0.07
    aka
    -0.07
     Everton
    -0.07
     Mira
    -0.07
     traduc
    -0.07
    elsen
    -0.07
     AUS
    -0.07
    ordin
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    abol
    0.08
     KOM
    0.08
     جز
    0.08
    scape
    0.07
    Berlin
    0.07
     fö
    0.07
     Kod
    0.07
     �
    0.07
     Berlin
    0.07
     Autob
    0.07
    Activations Density 0.003%

    No Known Activations