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. 328
    Prev
    Next
    INDEX
    Explanations

    n

    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
    Demo
    -0.08
    Trust
    -0.08
     trust
    -0.08
    握
    -0.07
    可信
    -0.07
    UDP
    -0.07
    .T
    -0.07
    Minimal
    -0.07
     rouge
    -0.07
    hew
    -0.07
    POSITIVE LOGITS
     Rece
    0.09
     Fade
    0.09
     поряд
    0.08
    @index
    0.08
     번호
    0.08
    OUNDS
    0.08
    نامه
    0.08
     kerana
    0.08
     получать
    0.08
    apers
    0.08
    Activations Density 0.030%

    No Known Activations