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. 9179
    Prev
    Next
    INDEX
    Explanations

    numerical ranges

    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
    лау
    -0.08
    ’év
    -0.08
     নেও
    -0.08
    řejmě
    -0.08
    ərək
    -0.08
     નથી
    -0.08
    کار
    -0.08
    آخر
    -0.08
     ران
    -0.07
     آخر
    -0.07
    POSITIVE LOGITS
     ext
    0.09
    .ar
    0.07
     Ext
    0.07
     atrop
    0.07
     Inform
    0.07
     Showtime
    0.07
     charla
    0.07
     నుం�
    0.07
     primeiros
    0.07
     Investor
    0.07
    Activations Density 0.056%

    No Known Activations