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. 49094
    Prev
    Next
    INDEX
    Explanations

    pairing, buddies

    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
     detection
    -0.08
     ب
    -0.07
    the
    -0.07
     dete
    -0.07
    ITIVE
    -0.07
    PLY
    -0.07
     confirming
    -0.07
    \[
    -0.07
     get
    -0.07
     vál
    -0.07
    POSITIVE LOGITS
     mentorship
    0.12
     mentoring
    0.12
    Pairs
    0.11
     Assigned
    0.10
     pairs
    0.10
     Pair
    0.10
     настав
    0.10
     mentors
    0.10
    pairs
    0.10
     mentor
    0.10
    Activations Density 0.023%

    No Known Activations