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. 15-RESID-POST-AA
    6. 19547
    Prev
    Next
    INDEX
    Explanations

    4

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     вещи
    -0.10
     things
    -0.09
     средства
    -0.08
     врем
    -0.08
    런
    -0.08
     резерв
    -0.08
     электро
    -0.08
     дальней
    -0.08
     ввод
    -0.08
     инстру
    -0.08
    POSITIVE LOGITS
    _orig
    0.09
     Sab
    0.08
     =
    0.08
     Braves
    0.08
     asal
    0.08
     :=
    0.08
    pn
    0.08
     എന്ന
    0.07
     defer
    0.07
    anoa
    0.07
    Activations Density 0.025%

    No Known Activations