© 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. 78811
    Prev
    Next
    INDEX
    Explanations

    end of snippet

    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
     nu
    -0.08
     preferential
    -0.08
    ilename
    -0.08
     Nu
    -0.07
    008
    -0.07
    SU
    -0.07
    044
    -0.07
    ิต
    -0.07
    abei
    -0.07
    xture
    -0.07
    POSITIVE LOGITS
     wanting
    0.14
     хочет
    0.13
     desire
    0.13
     ترغب
    0.13
     चाहते
    0.12
     desires
    0.12
     behoefte
    0.12
     muốn
    0.12
     dissatisfaction
    0.12
     ingin
    0.12
    Activations Density 0.197%

    No Known Activations