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. 53860
    Prev
    Next
    INDEX
    Explanations

    ual

    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
     keines
    -0.08
     طبیعی
    -0.08
     ---
    -0.08
     Vera
    -0.08
     zweiten
    -0.08
     درجة
    -0.08
     beil
    -0.08
     نہ
    -0.08
     نکرد
    -0.08
     dtype
    -0.08
    POSITIVE LOGITS
     brainstorm
    0.08
    描
    0.07
    @login
    0.07
    擦
    0.07
    人在
    0.07
    หน
    0.07
     foods
    0.07
     markets
    0.07
     opis
    0.07
     bwo
    0.07
    Activations Density 0.004%

    No Known Activations