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. 90308
    Prev
    Next
    INDEX
    Explanations

    on

    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
     Vag
    -0.08
     ничего
    -0.08
     alas
    -0.08
     Aka
    -0.08
     VT
    -0.07
     کا
    -0.07
     Ply
    -0.07
     passageiros
    -0.07
     spool
    -0.07
     σ
    -0.07
    POSITIVE LOGITS
    🏼
    0.09
    🏻
    0.08
     condiment
    0.08
     brat
    0.07
     Filip
    0.07
    Games
    0.07
    FTA
    0.07
    (inplace
    0.07
    Chron
    0.07
    istrict
    0.07
    Activations Density 0.002%

    No Known Activations