Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45679
    Prev
    Next
    INDEX
    Explanations

    mana

    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
    aled
    -0.08
     Alaska
    -0.07
    -fold
    -0.07
    star
    -0.07
     rate
    -0.06
    危
    -0.06
    -d
    -0.06
     эп
    -0.06
    agle
    -0.06
     star
    -0.06
    POSITIVE LOGITS
     للو
    0.09
     لتن
    0.09
     Potion
    0.09
     مني
    0.08
     جيڪو
    0.08
     الوصول
    0.08
     المختلفة
    0.08
     وتن
    0.08
    IUnknown
    0.08
     طبيعي
    0.08
    Activations Density 0.000%

    No Known Activations