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

    Neuronpedia

    APICircuit 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. 54029
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    	fi
    -0.08
    .Should
    -0.08
     Rite
    -0.08
     Gun
    -0.07
    碑
    -0.07
    _ca
    -0.07
     FAC
    -0.07
    .ts
    -0.07
    iyorum
    -0.07
     inciso
    -0.07
    POSITIVE LOGITS
     धन
    0.08
    _ZERO
    0.08
     qanday
    0.08
     Reflect
    0.07
    �
    0.07
    Reflect
    0.07
    .YELLOW
    0.07
     hers
    0.07
     ụtọ
    0.07
     өлк
    0.07
    Activations Density 0.001%

    No Known Activations