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. 112318
    Prev
    Next
    INDEX
    Explanations

    Period

    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
     Atr
    -0.08
     Anders
    -0.08
    创业
    -0.08
    -act
    -0.08
    OJ
    -0.08
    -empty
    -0.08
    $status
    -0.08
    หย
    -0.08
     માંગ
    -0.07
     বাবা
    -0.07
    POSITIVE LOGITS
    лең
    0.08
     inol
    0.07
     heavyweight
    0.07
     /\
    0.07
     blocking
    0.07
     vorz
    0.07
     />,↵
    0.07
    нод
    0.07
     trat
    0.07
     cir
    0.07
    Activations Density 0.017%

    No Known Activations