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. 78754
    Prev
    Next
    INDEX
    Explanations

    More

    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
     paras
    -0.09
     الض
    -0.08
     vague
    -0.07
     stationary
    -0.07
     иммун
    -0.07
    Paras
    -0.07
    )},↵
    -0.07
     Maroc
    -0.07
    igest
    -0.07
     autor
    -0.07
    POSITIVE LOGITS
    (metrics
    0.08
    เหนือ
    0.08
     celebrar
    0.08
    템
    0.08
    評論
    0.08
     მო
    0.08
     Reel
    0.08
    vlo
    0.08
     TEMPLATE
    0.08
     MOTOR
    0.07
    Activations Density 0.003%

    No Known Activations