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. 53944
    Prev
    Next
    INDEX
    Explanations

    matter

    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
     selling
    -0.09
    Selling
    -0.09
     Selling
    -0.08
     Offensive
    -0.08
     competitiveness
    -0.08
    selling
    -0.08
    jähr
    -0.08
     blaming
    -0.08
    dims
    -0.08
    .Native
    -0.08
    POSITIVE LOGITS
     electrons
    0.09
     vort
    0.08
     molecules
    0.08
    具有
    0.08
     imati
    0.08
     tard
    0.08
     Glide
    0.07
     billi
    0.07
     waves
    0.07
     atoms
    0.07
    Activations Density 0.005%

    No Known Activations