Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91054
    Prev
    Next
    INDEX
    Explanations

    and/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
    이
    -0.08
    .health
    -0.07
    과
    -0.07
     tere
    -0.07
     interest
    -0.07
     intéress
    -0.07
    နိုင်
    -0.07
     acclaim
    -0.07
    un
    -0.07
    jun
    -0.07
    POSITIVE LOGITS
    

    0.09
     Nottingham
    0.08
    .au
    0.08
     borne
    0.08
     skl
    0.08
    0.08
    }{↵
    0.07
     powering
    0.07
     angenommen
    0.07
    сан
    0.07
    Activations Density 0.067%

    No Known Activations