© 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. 108692
    Prev
    Next
    INDEX
    Explanations

    streaming

    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
     logiciel
    -0.08
     intérieur
    -0.08
     spettac
    -0.08
     sopr
    -0.08
     almeno
    -0.08
     bookstore
    -0.08
     jasa
    -0.08
     curator
    -0.08
     hump
    -0.07
     oa
    -0.07
    POSITIVE LOGITS
    -let
    0.07
    Declar
    0.07
    avings
    0.07
    ynchron
    0.07
    duled
    0.07
    ----↵↵
    0.07
    ੱਕ
    0.07
    Frames
    0.07
    كلة
    0.07
    -wide
    0.07
    Activations Density 0.013%

    No Known Activations