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. 60122
    Prev
    Next
    INDEX
    Explanations

    mathematical computation

    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
     overcame
    -0.08
     rund
    -0.07
     resolved
    -0.07
     CIA
    -0.07
    Resolved
    -0.07
     climbed
    -0.07
     robbed
    -0.07
     vandal
    -0.07
     Fisheries
    -0.07
     Newspapers
    -0.07
    POSITIVE LOGITS
     sposób
    0.09
     theoretically
    0.09
     always
    0.09
     hypothetical
    0.09
     depending
    0.09
    דרך
    0.09
    qondo
    0.08
     manière
    0.08
     relation
    0.08
     באופן
    0.08
    Activations Density 0.175%

    No Known Activations