© 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. 78470
    Prev
    Next
    INDEX
    Explanations

    cart

    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
     corona
    -0.08
    Chef
    -0.07
     tav
    -0.07
    終
    -0.07
     File
    -0.07
    版
    -0.07
     ل
    -0.07
     Fus
    -0.07
     Julie
    -0.07
     carta
    -0.07
    POSITIVE LOGITS
    esian
    0.10
     �
    0.09
     pog
    0.08
     linh
    0.08
    smanship
    0.08
     Gent
    0.08
    urgent
    0.08
     lasten
    0.07
     Bennett
    0.07
     phe
    0.07
    Activations Density 0.008%

    No Known Activations