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. 60960
    Prev
    Next
    INDEX
    Explanations

    wall

    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
     UICollection
    -0.08
     danse
    -0.08
     همکاری
    -0.08
     ecosystem
    -0.08
     esqu
    -0.08
     altru
    -0.08
    ுக
    -0.08
    gef
    -0.07
    -0.07
     اخلاق
    -0.07
    POSITIVE LOGITS
     suspension
    0.09
     поверхность
    0.09
    面积
    0.08
     frontage
    0.08
     Suspension
    0.08
     oppervlak
    0.08
     thickness
    0.08
     ప్రారంభ
    0.08
     Beitrag
    0.07
     Thickness
    0.07
    Activations Density 0.008%

    No Known Activations