© 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. 3-RESID-POST-AA
    11. 1298
    Prev
    Next
    INDEX
    Explanations

    Japanese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     registra
    -0.08
     Cp
    -0.08
    vention
    -0.07
    യ
    -0.07
     шы
    -0.07
     কাম
    -0.07
     نورو
    -0.07
     ника
    -0.07
     остав
    -0.07
     discounts
    -0.07
    POSITIVE LOGITS
     sing
    0.08
    uren
    0.08
    Comic
    0.07
    歌
    0.07
    Beauty
    0.07
    upil
    0.07
     mantle
    0.07
     ovar
    0.07
     �
    0.07
    comment
    0.07
    Activations Density 0.000%

    No Known Activations