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. 101561
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ändigen
    -0.09
     miracle
    -0.09
    -feira
    -0.08
    ipherals
    -0.08
     Interesse
    -0.08
     افراد
    -0.07
     fortuna
    -0.07
     Advocacy
    -0.07
     heavens
    -0.07
    関
    -0.07
    POSITIVE LOGITS
     acidic
    0.08
    .gold
    0.08
    Quad
    0.08
     gold
    0.08
     green
    0.08
    _dec
    0.07
     deco
    0.07
    SOL
    0.07
    dec
    0.07
     dec
    0.07
    Activations Density 0.013%

    No Known Activations