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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61053
    Prev
    Next
    INDEX
    Explanations

    bait

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     candle
    -0.09
     cinque
    -0.08
    трым
    -0.08
     Catal
    -0.07
     anch
    -0.07
     contiene
    -0.07
     contener
    -0.07
    所在
    -0.07
     catalyst
    -0.07
    情况下
    -0.07
    POSITIVE LOGITS
    раться
    0.08
    airport
    0.08
    college
    0.08
    adir
    0.08
     fó
    0.08
     Changing
    0.08
    ajax
    0.08
     busiest
    0.07
    artits
    0.07
     mafia
    0.07
    Activations Density 0.000%

    No Known Activations