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

    Neuronpedia

    APICircuit 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. 53988
    Prev
    Next
    INDEX
    Explanations

    canned

    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
     extent
    -0.08
     metam
    -0.08
     pente
    -0.08
     enact
    -0.08
    აქ
    -0.08
     stringent
    -0.07
     belasting
    -0.07
    čil
    -0.07
    anw
    -0.07
    ுக்
    -0.07
    POSITIVE LOGITS
    /text
    0.08
    206
    0.08
     soup
    0.08
     ur
    0.07
    bell
    0.07
     artesanal
    0.07
    Service
    0.07
     Steak
    0.07
     bay
    0.07
     лю
    0.07
    Activations Density 0.007%

    No Known Activations