© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129575
    Prev
    Next
    INDEX
    Explanations

    dot

    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
    widget
    -0.07
    ft
    -0.07
     Fil
    -0.07
    ŭ
    -0.07
     virus
    -0.07
    /settings
    -0.07
    ¥
    -0.06
    ור
    -0.06
    連
    -0.06
     ihm
    -0.06
    POSITIVE LOGITS
     combust
    0.09
     combustible
    0.08
     comprends
    0.08
    одол
    0.08
     Sonata
    0.08
    ательная
    0.08
    ��
    0.08
    имого
    0.08
     sarad
    0.08
     bombas
    0.08
    Activations Density 0.001%

    No Known Activations