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. 77140
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    urlar
    -0.09
    agram
    -0.07
    agrams
    -0.07
    nsk
    -0.07
     स्क
    -0.07
     they'll
    -0.07
     Stad
    -0.07
    ariki
    -0.07
    roger
    -0.07
    Cls
    -0.07
    POSITIVE LOGITS
    以及
    0.09
     valamint
    0.09
     illetve
    0.08
     그리고
    0.08
     καθώς
    0.08
     ועוד
    0.08
     пове
    0.07
    ματα
    0.07
    amot
    0.07
     "'",
    0.07
    Activations Density 0.047%

    No Known Activations