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. 60567
    Prev
    Next
    INDEX
    Explanations

    14

    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
     перес
    -0.09
     bearbeiten
    -0.07
     articles
    -0.07
     Sob
    -0.07
    issant
    -0.07
     услов
    -0.07
    irge
    -0.07
     SOC
    -0.07
     jou
    -0.07
     ru
    -0.07
    POSITIVE LOGITS
    准备
    0.09
     pribli
    0.09
    ضير
    0.09
    準
    0.09
     مرک
    0.08
     bydd
    0.08
    唐
    0.08
     կմ
    0.08
    dì
    0.08
     Vorbereitung
    0.08
    Activations Density 0.001%

    No Known Activations