© 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. 65335
    Prev
    Next
    INDEX
    Explanations

    Code snippets and explanations

    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
    ्ट्र
    -0.09
     ră
    -0.08
    打造
    -0.08
     naziv
    -0.08
     electricians
    -0.08
    ्ट्रेल
    -0.08
     nautical
    -0.08
    ינות
    -0.08
     kines
    -0.08
    ტრ
    -0.08
    POSITIVE LOGITS
     Bash
    0.08
     함수
    0.08
     useful
    0.08
    (x
    0.07
    .c
    0.07
    ase
    0.07
    (*
    0.07
     measurement
    0.07
    (origin
    0.07
    AL
    0.07
    Activations Density 0.013%

    No Known Activations