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. 76092
    Prev
    Next
    INDEX
    Explanations

    Taxes and real estate

    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
     HGH
    -0.08
     these
    -0.07
    ####
    -0.07
     veroorzaakt
    -0.07
    GH
    -0.07
    \CMS
    -0.07
     GH
    -0.07
     opmerkingen
    -0.07
    .XR
    -0.07
    Email
    -0.07
    POSITIVE LOGITS
    uisse
    0.08
     consideração
    0.08
    صلحة
    0.08
    íticas
    0.08
    wy
    0.08
    izin
    0.08
    ğan
    0.08
    saida
    0.08
    روض
    0.07
     Considering
    0.07
    Activations Density 0.000%

    No Known Activations