© 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. 3-RESID-POST-AA
    11. 1360
    Prev
    Next
    INDEX
    Explanations

    Counting and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TH
    -0.09
    ________________________________
    -0.08
    äh
    -0.08
    勿
    -0.07
     исполн
    -0.07
     Scarlett
    -0.07
    ~~~~~~~~~~~~~~~~
    -0.07
     gears
    -0.07
    isp
    -0.07
    京
    -0.07
    POSITIVE LOGITS
    prijzen
    0.08
     manje
    0.07
     ruler
    0.07
    عراض
    0.07
    	flags
    0.07
     rabbit
    0.07
     prijzen
    0.07
     Duk
    0.07
    bu
    0.07
    	errors
    0.07
    Activations Density 0.000%

    No Known Activations