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. 53048
    Prev
    Next
    INDEX
    Explanations

    bis

    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
     anth
    -0.09
     spé
    -0.08
     anaer
    -0.08
    ولی
    -0.08
     avid
    -0.07
     heterogeneous
    -0.07
     ảnh
    -0.07
     أح
    -0.07
    Bul
    -0.07
     torr
    -0.07
    POSITIVE LOGITS
     administrador
    0.08
    	throw
    0.08
     Dia
    0.07
    pcm
    0.07
     Reject
    0.07
    woch
    0.07
     Familie
    0.07
    čio
    0.07
     NEG
    0.07
    ystems
    0.07
    Activations Density 0.003%

    No Known Activations