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. 41986
    Prev
    Next
    INDEX
    Explanations

    Unusual performances/acts

    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
     রয়েছে
    -0.08
    xxxxxxxx
    -0.07
    ਉ
    -0.07
    ulty
    -0.07
     אשר
    -0.07
     við
    -0.07
    τικό
    -0.07
    entes
    -0.07
    xxxxx
    -0.07
    ুট
    -0.07
    POSITIVE LOGITS
    687
    0.08
    Projected
    0.08
    Projectile
    0.08
     Project
    0.08
     Projection
    0.07
     explode
    0.07
     उत्क
    0.07
     freak
    0.07
     विशेषज्ञ
    0.07
     kert
    0.07
    Activations Density 0.003%

    No Known Activations