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. 119729
    Prev
    Next
    INDEX
    Explanations

    trans

    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
     punishment
    -0.10
     jumlah
    -0.08
     구현
    -0.08
    Usually
    -0.08
     hängen
    -0.08
    uitas
    -0.08
     intent
    -0.08
     vermitteln
    -0.08
     kasus
    -0.08
    Subject
    -0.08
    POSITIVE LOGITS
    毎
    0.08
    走势
    0.08
    _REFRESH
    0.08
     Upcoming
    0.08
     upcoming
    0.08
    rossover
    0.08
     highs
    0.08
     Astros
    0.08
     highlighted
    0.08
     boosters
    0.08
    Activations Density 0.012%

    No Known Activations