Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43761
    Prev
    Next
    INDEX
    Explanations

    Foreign languages, informal speech

    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
     péné
    -0.09
     penetration
    -0.09
     penile
    -0.09
    penetr
    -0.08
     penetr
    -0.08
     jährlich
    -0.08
     annually
    -0.08
     penetrating
    -0.08
     संव
    -0.08
    ™,
    -0.08
    POSITIVE LOGITS
     errands
    0.19
     शनिवार
    0.14
     बुधवार
    0.13
     शुक्रवार
    0.13
     sábado
    0.13
     सोमवार
    0.12
     dinner
    0.12
    忙
    0.12
     오후
    0.12
    下午
    0.12
    Activations Density 0.080%

    No Known Activations