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. 88181
    Prev
    Next
    INDEX
    Explanations

    us

    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
    .validate
    -0.08
     pente
    -0.08
     Slave
    -0.07
     إطار
    -0.07
     Nesse
    -0.07
    slave
    -0.07
     logs
    -0.07
     transformation
    -0.07
    erschap
    -0.07
    είο
    -0.07
    POSITIVE LOGITS
    �
    0.09
     tou
    0.08
     sharply
    0.08
     birlikte
    0.08
     pá
    0.07
     utan
    0.07
     を
    0.07
    long
    0.07
    OM
    0.07
     torn
    0.07
    Activations Density 0.014%

    No Known Activations