© 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. 95180
    Prev
    Next
    INDEX
    Explanations

    polishing

    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
     reopen
    -0.08
     acondicionado
    -0.07
     getattr
    -0.07
     landlord
    -0.07
     destacado
    -0.07
     Glaub
    -0.07
     stack
    -0.07
     Gér
    -0.07
    рой
    -0.07
     landlords
    -0.07
    POSITIVE LOGITS
    0.09
     नियम
    0.09
    0.09
    691
    0.08
    Able
    0.08
    �
    0.08
     Lyme
    0.08
     पुरस्कार
    0.08
     praises
    0.08
    0.08
    Activations Density 0.002%

    No Known Activations