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. 98214
    Prev
    Next
    INDEX
    Explanations

    say the ending -ender or ul

    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
    ekayo
    -0.09
    Յ
    -0.08
    èo
    -0.08
    wati
    -0.08
     senhor
    -0.08
     hardships
    -0.08
    ၂၀
    -0.08
    յանի
    -0.08
    ունակում
    -0.07
     Gong
    -0.07
    POSITIVE LOGITS
    ender
    0.15
    enders
    0.12
    ange
    0.10
    ul
    0.10
    ference
    0.09
    anged
    0.09
    asher
    0.08
    ave
    0.08
    avings
    0.08
    amas
    0.08
    Activations Density 0.002%

    No Known Activations