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. 102818
    Prev
    Next
    INDEX
    Explanations

    1

    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
    Certainly
    -0.08
    MV
    -0.08
     voort
    -0.07
    lığ
    -0.07
     Certainly
    -0.07
     plentiful
    -0.07
     démarches
    -0.07
     Einfach
    -0.07
    VW
    -0.07
     modernas
    -0.07
    POSITIVE LOGITS
    |}↵
    0.08
    |.↵
    0.08
    .deepcopy
    0.07
     сентября
    0.07
     favorite
    0.07
    ొక్క
    0.07
    |"
    0.07
     thereby
    0.07
    сон
    0.07
     поэтому
    0.07
    Activations Density 0.148%

    No Known Activations