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. 54150
    Prev
    Next
    INDEX
    Explanations

    Directory information and sequencing

    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
    FACE
    -0.07
    -0.07
    quilla
    -0.07
    ុ
    -0.07
     Immun
    -0.07
     gars
    -0.07
    arring
    -0.07
    Cookie
    -0.07
     Display
    -0.07
     Your
    -0.07
    POSITIVE LOGITS
    经营
    0.09
     blok
    0.09
     African
    0.08
     اعتماد
    0.08
    Verdana
    0.08
    ανα
    0.08
     Afrika
    0.08
     فکر
    0.08
     Emilia
    0.08
    لاک
    0.08
    Activations Density 0.001%

    No Known Activations