© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48508
    Prev
    Next
    INDEX
    Explanations

    diacritics

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‭
    -0.12
    �
    -0.12
    �
    -0.12
    Α
    -0.12
          
    -0.12
    ་�
    -0.11
    ワ
    -0.11
    Ι
    -0.11
        
    -0.11
    Ν
    -0.11
    POSITIVE LOGITS
     ҙ
    0.13
     ҿ
    0.12
     ҵ
    0.11
     ýö
    0.10
     ź
    0.10
     ҩ
    0.10
     ő
    0.09
    øð
    0.09
     ý
    0.09
     ļ
    0.09
    Activations Density 0.004%

    No Known Activations