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. 15-RESID-POST-AA
    6. 95
    Prev
    Next
    INDEX
    Explanations

    period

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -এর
    -0.08
     femin
    -0.08
    jø
    -0.07
    &
    -0.07
     యొక్క
    -0.07
    club
    -0.07
    emain
    -0.07
    etta
    -0.07
     fémin
    -0.07
     игр
    -0.07
    POSITIVE LOGITS
     področ
    0.08
    었던
    0.08
     topic
    0.08
     વિસ્ત
    0.08
     ngata
    0.07
     cave
    0.07
     tópico
    0.07
     회
    0.07
     пунк
    0.07
    ำเภ
    0.07
    Activations Density 0.001%

    No Known Activations