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. 88023
    Prev
    Next
    INDEX
    Explanations

    Numbers in the 50s

    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
    गार
    -0.09
     Sacred
    -0.08
     bub
    -0.08
     gen
    -0.08
    �
    -0.08
     বিস
    -0.08
    buddy
    -0.08
     ca
    -0.07
     superb
    -0.07
     Eck
    -0.07
    POSITIVE LOGITS
    Hat
    0.08
    TA
    0.08
    তম
    0.08
     Hat
    0.07
    Wanted
    0.07
    ต้อง
    0.07
     conhecer
    0.07
     finalist
    0.07
     от
    0.07
     Ur
    0.07
    Activations Density 0.096%

    No Known Activations