© 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. 94841
    Prev
    Next
    INDEX
    Explanations

    same melody

    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
     daher
    -0.09
     ungewöhn
    -0.08
     vtk
    -0.08
    ivität
    -0.08
     التعاون
    -0.08
     가능
    -0.08
     Durch
    -0.08
     nedeniyle
    -0.08
     durchgeführt
    -0.08
     כי
    -0.08
    POSITIVE LOGITS
     estrutura
    0.10
     struttura
    0.09
    eyey
    0.08
     structure
    0.08
     originally
    0.08
     to
    0.08
     estructura
    0.08
    erta
    0.08
     adaptée
    0.08
     iconic
    0.08
    Activations Density 0.017%

    No Known Activations