© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8148
    Prev
    Next
    INDEX
    Explanations

    with

    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
     rew
    -0.08
     Gunnar
    -0.08
     thereafter
    -0.08
    celand
    -0.07
     danach
    -0.07
    �
    -0.07
     caves
    -0.07
     angesch
    -0.07
    reta
    -0.07
    ాత్ర
    -0.07
    POSITIVE LOGITS
     company's
    0.09
     Company's
    0.08
     odpowied
    0.08
    公司的
    0.08
    来自
    0.08
    Actual
    0.08
     practition
    0.07
     настоящ
    0.07
     நடை
    0.07
     savvy
    0.07
    Activations Density 0.014%

    No Known Activations