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. 30507
    Prev
    Next
    INDEX
    Explanations

    norm or proto

    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
    coll
    -0.08
    details
    -0.08
     ভাগ
    -0.08
    ματος
    -0.07
     coll
    -0.07
     બનાવ
    -0.07
     bud
    -0.07
     randomly
    -0.07
     postar
    -0.07
    Detal
    -0.07
    POSITIVE LOGITS
     لغ
    0.08
     adelant
    0.08
     крип
    0.07
     Streams
    0.07
     Cub
    0.07
    급
    0.07
    Reads
    0.07
    ynyň
    0.07
     poslu
    0.07
    Works
    0.07
    Activations Density 0.001%

    No Known Activations