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. 45317
    Prev
    Next
    INDEX
    Explanations

    sh

    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
     Aval
    -0.09
     От
    -0.08
    antai
    -0.08
     Heat
    -0.08
     Мин
    -0.08
     əldə
    -0.08
     DO
    -0.08
     Kv
    -0.08
     نقل
    -0.08
     എന്നാല്
    -0.08
    POSITIVE LOGITS
    directory
    0.08
    ly
    0.08
    usable
    0.08
    ်
    0.07
    right
    0.07
    their
    0.07
    measurement
    0.07
    exper
    0.07
    иша
    0.07
    greater
    0.07
    Activations Density 0.066%

    No Known Activations