Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45157
    Prev
    Next
    INDEX
    Explanations

    insertion sort

    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
    ób
    -0.08
     vyb
    -0.08
     equipped
    -0.08
    .Sync
    -0.08
     visitation
    -0.07
    ulario
    -0.07
    Visited
    -0.07
    touch
    -0.07
     resurgence
    -0.07
    版权所有
    -0.07
    POSITIVE LOGITS
     insertion
    0.13
    Insertion
    0.13
    sertion
    0.13
     inserting
    0.12
     insertar
    0.12
     insert
    0.11
     inserir
    0.11
     встав
    0.11
    _insert
    0.11
     Placement
    0.11
    Activations Density 0.010%

    No Known Activations