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. 112161
    Prev
    Next
    INDEX
    Explanations

    public

    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
     curl
    -0.08
     oc
    -0.08
     scen
    -0.08
     sobe
    -0.08
     h
    -0.07
     때
    -0.07
    (QObject
    -0.07
     oauth
    -0.07
    Anne
    -0.07
     hệ
    -0.07
    POSITIVE LOGITS
    veyor
    0.09
     Мор
    0.08
     мор
    0.08
    ଭ
    0.08
    0.07
     disastr
    0.07
     Records
    0.07
     Leon
    0.07
     Src
    0.07
    Records
    0.07
    Activations Density 0.001%

    No Known Activations