© 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. 48203
    Prev
    Next
    INDEX
    Explanations

    aga

    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
    ignons
    -0.09
    ्च
    -0.08
    ückt
    -0.08
    janje
    -0.08
    ्चर
    -0.08
    geois
    -0.08
     allure
    -0.07
    /D
    -0.07
    eca
    -0.07
    ್ಚ
    -0.07
    POSITIVE LOGITS
    aga
    0.09
    λή
    0.08
     îl
    0.08
     laag
    0.08
     haa
    0.08
    ofar
    0.07
    สนาม
    0.07
     هوا
    0.07
    IGH
    0.07
     Taliban
    0.07
    Activations Density 0.001%

    No Known Activations