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

    Neuronpedia

    APICircuit 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. 12957
    Prev
    Next
    INDEX
    Explanations

    8

    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
    ismatic
    -0.08
    quipment
    -0.08
     Wuhan
    -0.08
     HVAC
    -0.07
     kcal
    -0.07
    ucose
    -0.07
     vody
    -0.07
     Fahrrad
    -0.07
    714
    -0.07
    quoise
    -0.07
    POSITIVE LOGITS
    (Debug
    0.08
    (Vec
    0.08
     legislative
    0.08
    Vectors
    0.08
     acting
    0.07
     במד
    0.07
     purpos
    0.07
    Tracing
    0.07
    _vec
    0.07
     deput
    0.07
    Activations Density 0.000%

    No Known Activations