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. 54450
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ाऊ
    -0.08
    363
    -0.07
     born
    -0.07
    	unset
    -0.07
    287
    -0.07
     Loop
    -0.07
    �
    -0.07
    وعية
    -0.07
     wealth
    -0.07
    ,以及
    -0.07
    POSITIVE LOGITS
     написал
    0.09
    เอ็ม
    0.08
     작성
    0.08
     առաջարկ
    0.08
     encontrarás
    0.08
    peyan
    0.08
     구현
    0.08
    annen
    0.08
     제작
    0.08
    nyň
    0.08
    Activations Density 0.013%

    No Known Activations