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. 113911
    Prev
    Next
    INDEX
    Explanations

    yle

    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
    invent
    -0.08
     fe
    -0.08
    ths
    -0.08
    	goto
    -0.07
     differenti
    -0.07
     ass
    -0.07
     కన్న
    -0.07
    inventory
    -0.07
     reinc
    -0.07
    fe
    -0.07
    POSITIVE LOGITS
    চ্চ
    0.08
     MEC
    0.08
    ellte
    0.08
     ujum
    0.08
     ppt
    0.08
    ել
    0.08
    ුර
    0.08
    мач
    0.08
     PIT
    0.08
     dangere
    0.08
    Activations Density 0.000%

    No Known Activations