© 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. 23-RESID-POST-AA
    11. 5858
    Prev
    Next
    INDEX
    Explanations

    dark mode

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     شن
    -0.08
     إقامة
    -0.08
     offer
    -0.08
     Offer
    -0.08
    033
    -0.08
     Vaccine
    -0.08
     вок
    -0.08
    �
    -0.07
     hospitalization
    -0.07
     establishing
    -0.07
    POSITIVE LOGITS
     dark
    0.09
    Dark
    0.09
    dark
    0.09
     metallic
    0.08
     Dark
    0.08
    -dark
    0.08
     futuro
    0.08
    Future
    0.08
     DARK
    0.08
     plugins
    0.08
    Activations Density 0.001%

    No Known Activations