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. 3-RESID-POST-AA
    6. 1876
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     máy
    -0.08
    Organizations
    -0.08
     day's
    -0.07
     المف
    -0.07
    ctomy
    -0.07
     Artemis
    -0.07
     organizations
    -0.07
     xen
    -0.07
    ਰਾ
    -0.07
     serviced
    -0.07
    POSITIVE LOGITS
    푸
    0.08
     simplicity
    0.08
     subsidies
    0.08
     sce
    0.08
     profund
    0.08
     만
    0.08
     unl
    0.08
    emp
    0.07
     w
    0.07
    prent
    0.07
    Activations Density 0.063%

    No Known Activations