© 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. 6140
    Prev
    Next
    INDEX
    Explanations

    say "ucumber"

    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
     cocaine
    -0.08
    acial
    -0.08
    ఏ
    -0.08
     petróleo
    -0.08
     карта
    -0.08
     fari
    -0.08
     Coca
    -0.08
     tá
    -0.08
     toque
    -0.08
    ΑΣ
    -0.08
    POSITIVE LOGITS
    ucumber
    0.23
    uc
    0.15
    uke
    0.14
    eleri
    0.11
    UC
    0.11
    abb
    0.11
    ress
    0.10
     cucumber
    0.09
    antal
    0.09
    uksi
    0.09
    Activations Density 0.002%

    No Known Activations