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. 106118
    Prev
    Next
    INDEX
    Explanations

    :

    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
     الإث
    -0.08
    。这
    -0.08
     lee
    -0.08
     열
    -0.07
    는
    -0.07
     configur
    -0.07
    。因此
    -0.07
     variété
    -0.07
    اپ
    -0.07
     것은
    -0.07
    POSITIVE LOGITS
     Seed
    0.08
    Plants
    0.08
     Securities
    0.08
    प्रधान
    0.08
     versehen
    0.07
     consumm
    0.07
    Seed
    0.07
     tangata
    0.07
     seed
    0.07
     risking
    0.07
    Activations Density 0.000%

    No Known Activations