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. 43420
    Prev
    Next
    INDEX
    Explanations

    furn

    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
     genetic
    -0.07
     fortal
    -0.07
    ян
    -0.07
     magnetic
    -0.07
    à
    -0.07
     contexts
    -0.07
    െയ്
    -0.07
    -0.07
    vika
    -0.07
     K
    -0.06
    POSITIVE LOGITS
    .“↵↵
    0.09
    .’↵↵
    0.09
    ,''
    0.09
    ;;;
    0.08
    ।”↵↵
    0.08
     】↵↵
    0.08
     menunjukkan
    0.08
     Slovakia
    0.08
     দেখ
    0.08
    	cnt
    0.08
    Activations Density 0.000%

    No Known Activations