© 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. 23-RESID-POST-AA
    11. 96923
    Prev
    Next
    INDEX
    Explanations

    只

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     może
    -0.08
     m
    -0.08
     fof
    -0.07
    def
    -0.07
    can
    -0.07
    ustin
    -0.07
    ijdt
    -0.07
    ator
    -0.07
    ，可以
    -0.07
     可以
    -0.07
    POSITIVE LOGITS
    要
    0.22
     要
    0.16
    只
    0.14
    ，要
    0.11
     zolang
    0.11
     طال
    0.11
    如
    0.10
     요
    0.10
    ，只
    0.10
    Как
    0.10
    Activations Density 0.002%

    No Known Activations