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. 23-RESID-POST-AA
    6. 130781
    Prev
    Next
    INDEX
    Explanations

    perme

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *u
    -0.08
     spherical
    -0.08
     epochs
    -0.08
     outr
    -0.08
    ueve
    -0.08
     megt
    -0.08
    ,u
    -0.08
    zungen
    -0.08
    ાર્�
    -0.07
    ర్స్
    -0.07
    POSITIVE LOGITS
    select
    0.10
     selective
    0.09
    лими
    0.09
    able
    0.09
    houses
    0.08
    oporosis
    0.08
    াহী
    0.08
    _water
    0.08
    leding
    0.08
    vious
    0.08
    Activations Density 0.001%

    No Known Activations