© 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. 48682
    Prev
    Next
    INDEX
    Explanations

    什

    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
    ated
    -0.10
    ates
    -0.08
    ater
    -0.08
    itatea
    -0.08
    dance
    -0.08
    adah
    -0.08
    année
    -0.08
    ating
    -0.08
    ணம்
    -0.07
    ettes
    -0.07
    POSITIVE LOGITS
    麼
    0.21
    �
    0.15
    樣
    0.10
     �
    0.10
    么
    0.09
    ιος
    0.09
    ‍മ
    0.08
     то
    0.08
    ова
    0.08
    то
    0.08
    Activations Density 0.001%

    No Known Activations