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. 97097
    Prev
    Next
    INDEX
    Explanations

    Russian

    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
    ери
    -0.08
    Pal
    -0.08
    ery
    -0.08
    iras
    -0.07
    eriya
    -0.07
    inez
    -0.07
    çadas
    -0.07
    érie
    -0.07
    ERICA
    -0.07
    ERRY
    -0.07
    POSITIVE LOGITS
    гию
    0.10
    hod
    0.10
    genic
    0.10
    ubin
    0.09
    хий
    0.08
    rh
    0.08
     읽
    0.08
     readership
    0.08
    hythm
    0.08
    �ಿ
    0.08
    Activations Density 0.009%

    No Known Activations