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. 23-RESID-POST-AA
    6. 98001
    Prev
    Next
    INDEX
    Explanations

    st

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ீத
    -0.08
     appliances
    -0.08
     ponds
    -0.08
     올
    -0.08
     apnea
    -0.08
     Appliances
    -0.08
     piles
    -0.07
     fences
    -0.07
     virou
    -0.07
    塘
    -0.07
    POSITIVE LOGITS
    ellar
    0.16
    ard
    0.15
    arg
    0.14
    arl
    0.14
    ાર્�
    0.13
    arm
    0.13
    ELL
    0.12
    ell
    0.12
    ARD
    0.12
    ellation
    0.11
    Activations Density 0.007%

    No Known Activations