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. 15-RESID-POST-AA
    6. 171
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.09
    	throws
    -0.09
     અંગે
    -0.09
    ifen
    -0.09
    ,nil
    -0.08
     بارے
    -0.08
    _in
    -0.08
    dä
    -0.08
    żu
    -0.08
     туралы
    -0.08
    POSITIVE LOGITS
     argent
    0.07
     Ring
    0.07
    :
    ↵//
    0.07
    ак
    0.07
     Jog
    0.07
    utorial
    0.07
      
    ↵
    0.06
     membuka
    0.06
    。,
    0.06
    ();
    ↵//
    0.06
    Activations Density 0.006%

    No Known Activations