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. 78064
    Prev
    Next
    INDEX
    Explanations

    code/formatting

    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
     cages
    -0.08
     Boise
    -0.08
     Mister
    -0.07
    -0.07
     Ramirez
    -0.07
     �
    -0.07
     Rubin
    -0.07
     consultants
    -0.07
     Renting
    -0.07
     Bog
    -0.07
    POSITIVE LOGITS
     tanpa
    0.10
    without
    0.10
     tightly
    0.10
     without
    0.10
     ohne
    0.09
     tighter
    0.09
     ללא
    0.09
    _without
    0.09
     WITHOUT
    0.09
     tight
    0.09
    Activations Density 0.044%

    No Known Activations