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. 3-RESID-POST-AA
    6. 12507
    Prev
    Next
    INDEX
    Explanations

    luggage

    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
    Implicit
    -0.08
     zaj
    -0.08
    Ful
    -0.08
     Zag
    -0.07
     NAM
    -0.07
    Extent
    -0.07
     cds
    -0.07
     jot
    -0.07
     sco
    -0.07
    ethi
    -0.07
    POSITIVE LOGITS
     Marian
    0.08
     tid
    0.08
     cosa
    0.08
    �
    0.07
     ук
    0.07
    יך
    0.07
     divers
    0.07
     immobil
    0.07
     peu
    0.07
    èy
    0.07
    Activations Density 0.003%

    No Known Activations