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. 15-RESID-POST-AA
    6. 19020
    Prev
    Next
    INDEX
    Explanations

    Ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ohner
    -0.08
    oth
    -0.07
     CAM
    -0.07
     framework
    -0.07
     robust
    -0.07
     Pic
    -0.06
    扩大
    -0.06
     ±
    -0.06
     models
    -0.06
     analytic
    -0.06
    POSITIVE LOGITS
     종료
    0.11
     конце
    0.11
     마지막
    0.11
     അവസാന
    0.11
     نهاية
    0.11
     پایان
    0.11
     trailing
    0.11
    -ending
    0.10
    ENDIF
    0.10
     aftermath
    0.10
    Activations Density 0.010%

    No Known Activations