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. 106167
    Prev
    Next
    INDEX
    Explanations

    concaten

    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
    Գ
    -0.08
     asynchronously
    -0.08
    Pseudo
    -0.07
     trademark
    -0.07
    RGCTX
    -0.07
    '].'"
    -0.07
    matige
    -0.07
     Parlement
    -0.07
     asynchronous
    -0.07
    ASY
    -0.07
    POSITIVE LOGITS
     fenomen
    0.08
     pona
    0.08
     Constructs
    0.07
    ,让
    0.07
    ,共
    0.07
     Sushi
    0.07
    、人
    0.07
     phénom
    0.07
     sapien
    0.07
    .headers
    0.07
    Activations Density 0.007%

    No Known Activations