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. 23074
    Prev
    Next
    INDEX
    Explanations

    mind

    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
    性生活
    -0.08
    وفير
    -0.08
     dependencia
    -0.08
     Neb
    -0.07
    ificar
    -0.07
     Author
    -0.07
    belt
    -0.07
    -0.07
    oen
    -0.07
     entretien
    -0.07
    POSITIVE LOGITS
    想着
    0.08
    却
    0.08
     incess
    0.07
    _Copy
    0.07
     tapestry
    0.07
     desperately
    0.07
    (Messages
    0.07
     переб
    0.07
    ეს
    0.07
     received
    0.07
    Activations Density 0.014%

    No Known Activations