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. 111668
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    LOGGER
    -0.08
    ать
    -0.07
    	LOGGER
    -0.07
     LOGGER
    -0.07
    	Output
    -0.07
     Goodman
    -0.07
    ổ
    -0.07
    734
    -0.07
     suggestion
    -0.07
    _EM
    -0.07
    POSITIVE LOGITS
     접근
    0.09
    播放
    0.09
     intimidating
    0.08
    易
    0.08
     reproducción
    0.08
     읽
    0.08
     resistant
    0.08
    -resistant
    0.08
     제작
    0.08
     rekke
    0.08
    Activations Density 0.039%

    No Known Activations