© 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. 75509
    Prev
    Next
    INDEX
    Explanations

    Access and permissions

    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
     მოქ
    -0.08
     خات
    -0.08
    valho
    -0.08
    Cant
    -0.08
    ండ్ర
    -0.08
    伏
    -0.08
    -el
    -0.08
    ersoq
    -0.08
    ლოგ
    -0.08
    CRUD
    -0.07
    POSITIVE LOGITS
     đủ
    0.09
     privilege
    0.08
     registrados
    0.08
    -approved
    0.08
     permiso
    0.08
    icient
    0.08
    authorized
    0.08
    permission
    0.08
     authorized
    0.08
     permission
    0.08
    Activations Density 0.088%

    No Known Activations