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. 61285
    Prev
    Next
    INDEX
    Explanations

    separate

    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
    versal
    -0.08
     형
    -0.07
    /music
    -0.07
    Whatever
    -0.07
     cds
    -0.07
     mons
    -0.07
     Desert
    -0.07
    truck
    -0.07
     быстро
    -0.07
    ofile
    -0.07
    POSITIVE LOGITS
    -अलग
    0.15
     biệt
    0.11
     vone
    0.09
     separate
    0.08
     અલગ
    0.08
     Carr
    0.08
     footing
    0.08
     ej
    0.07
     seperate
    0.07
     corona
    0.07
    Activations Density 0.016%

    No Known Activations