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. 43798
    Prev
    Next
    INDEX
    Explanations

    hypnotherapy

    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
     proizv
    -0.08
    bone
    -0.08
    [(
    -0.07
    pack
    -0.07
     lone
    -0.07
    ancio
    -0.07
     bedeut
    -0.07
     সরকারি
    -0.07
     packed
    -0.07
    	private
    -0.07
    POSITIVE LOGITS
     hypnosis
    0.09
     Dolores
    0.09
     garn
    0.09
     вашу
    0.08
     терап
    0.08
     Mik
    0.08
    Regards
    0.08
     Carn
    0.08
    Carn
    0.08
    Php
    0.08
    Activations Density 0.005%

    No Known Activations