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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112892
    Prev
    Next
    INDEX
    Explanations

    KA

    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
    er's
    -0.08
    _res
    -0.08
    amag
    -0.08
     religieux
    -0.08
    Exterior
    -0.08
     trase
    -0.07
     の
    -0.07
    ®.
    -0.07
    his
    -0.07
    itious
    -0.07
    POSITIVE LOGITS
     sensor
    0.08
     Pix
    0.08
     verw
    0.07
     </>↵
    0.07
    ;↵//↵//
    0.07
     breathing
    0.07
     وصول
    0.07
    0.07
    typeof
    0.07
     car
    0.07
    Activations Density 0.000%

    No Known Activations