© 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. 75482
    Prev
    Next
    INDEX
    Explanations

    не

    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
     Eins
    -0.08
     carreg
    -0.08
     Gemüse
    -0.08
     weiteres
    -0.08
     때문에
    -0.08
     показывает
    -0.08
    を見る
    -0.08
     Naj
    -0.07
     Artwork
    -0.07
     Documento
    -0.07
    POSITIVE LOGITS
     ли
    0.13
    _I
    0.07
     дав
    0.07
     nanot
    0.07
     indeed
    0.07
    ọ
    0.07
    ת
    0.07
     acaso
    0.07
    ánica
    0.07
     obstacles
    0.07
    Activations Density 0.004%

    No Known Activations