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. 46437
    Prev
    Next
    INDEX
    Explanations

    change or remain the same

    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
     Kole
    -0.08
     워
    -0.07
     rire
    -0.07
     negativity
    -0.07
     administrador
    -0.07
     Everest
    -0.07
     ange
    -0.07
     wehe
    -0.07
     Norris
    -0.07
     sedang
    -0.07
    POSITIVE LOGITS
     unchanged
    0.20
     그대로
    0.13
    unch
    0.12
     gebleven
    0.12
     retains
    0.11
     একই
    0.11
     remained
    0.11
    变化
    0.11
     అదే
    0.11
    Same
    0.11
    Activations Density 0.088%

    No Known Activations