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. 67347
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     tr
    -0.08
    kitty
    -0.08
    izan
    -0.08
     inclus
    -0.08
     thereby
    -0.07
    delen
    -0.07
    etha
    -0.07
     presidencial
    -0.07
    �
    -0.07
    teger
    -0.07
    POSITIVE LOGITS
     maupun
    0.11
     లేదా
    0.11
     hoặc
    0.10
     έως
    0.10
     أو
    0.10
     onwards
    0.10
     və
    0.10
     അല്ല
    0.10
     മുതൽ
    0.10
     અથવા
    0.10
    Activations Density 0.157%

    No Known Activations