Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98168
    Prev
    Next
    INDEX
    Explanations

    совп

    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
    ેબ
    -0.09
    ិប
    -0.08
    емой
    -0.08
    ెంట్
    -0.08
     jus
    -0.07
    ясь
    -0.07
    ycled
    -0.07
     सांस
    -0.07
    rechter
    -0.07
    jí
    -0.07
    POSITIVE LOGITS
    адают
    0.20
    адает
    0.19
    ад
    0.15
    ада
    0.12
    ало
    0.11
    асть
    0.10
    ала
    0.09
    адки
    0.09
    idenza
    0.09
    па
    0.08
    Activations Density 0.001%

    No Known Activations