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. 49247
    Prev
    Next
    INDEX
    Explanations

    Logical reasoning problems

    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
     sost
    -0.08
     wahrscheinlich
    -0.08
     ASAP
    -0.08
     hind
    -0.08
     ITS
    -0.07
     अझ
    -0.07
    	void
    -0.07
     unterscheiden
    -0.07
     sär
    -0.07
    。因此
    -0.07
    POSITIVE LOGITS
    +y
    0.09
    ,:
    0.08
    +w
    0.08
     ressalt
    0.08
    儿
    0.08
    coat
    0.07
     Carte
    0.07
    +x
    0.07
    Carte
    0.07
    +')
    0.07
    Activations Density 0.094%

    No Known Activations