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. 49777
    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
     सूचना
    -0.09
    adam
    -0.08
     sombra
    -0.08
    adamu
    -0.07
     très
    -0.07
    .Notification
    -0.07
     voir
    -0.07
    -0.07
    notification
    -0.07
     chut
    -0.07
    POSITIVE LOGITS
     снова
    0.12
     again
    0.10
     আবার
    0.09
     наоборот
    0.09
     ಮತ್ತೆ
    0.09
     nuevamente
    0.09
    Ley
    0.08
    Again
    0.08
     Cells
    0.08
     ફરી
    0.08
    Activations Density 0.081%

    No Known Activations