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. 58305
    Prev
    Next
    INDEX
    Explanations

    packing

    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
     pron
    -0.08
     dirig
    -0.07
     wählen
    -0.07
     aç
    -0.07
     обращаться
    -0.07
    loops
    -0.07
     levant
    -0.07
     direcion
    -0.07
     Stre
    -0.07
    itter
    -0.07
    POSITIVE LOGITS
    -packed
    0.13
     packed
    0.11
     accommodated
    0.11
    _pack
    0.11
     Packed
    0.10
    .pack
    0.10
    Packed
    0.10
     packing
    0.10
    Packing
    0.10
    -pack
    0.10
    Activations Density 0.028%

    No Known Activations