© 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. 578
    Prev
    Next
    INDEX
    Explanations

    or

    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
    Basics
    -0.10
     who've
    -0.09
    Ways
    -0.08
     sob
    -0.08
     posteriores
    -0.08
     morts
    -0.08
     roses
    -0.08
    воз
    -0.08
     ulcers
    -0.08
     torr
    -0.08
    POSITIVE LOGITS
     окно
    0.08
     datap
    0.08
     vacancy
    0.08
     जिसे
    0.08
     जिसके
    0.08
     fenêtre
    0.08
     commentary
    0.07
     itiner
    0.07
     Mean
    0.07
     kein
    0.07
    Activations Density 0.101%

    No Known Activations