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. 440
    Prev
    Next
    INDEX
    Explanations

    early

    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
     militia
    -0.08
    hto
    -0.08
    ītu
    -0.08
    heth
    -0.08
     Crest
    -0.07
    urs
    -0.07
     Belgique
    -0.07
    召
    -0.07
    halten
    -0.07
     בת
    -0.07
    POSITIVE LOGITS
     plastik
    0.09
     smoother
    0.08
     전체
    0.08
     unmittel
    0.08
     seamless
    0.08
     tốt
    0.08
     immediately
    0.08
    �
    0.08
     emuls
    0.08
     건
    0.08
    Activations Density 0.012%

    No Known Activations