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. 130815
    Prev
    Next
    INDEX
    Explanations

    CN

    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
    otation
    -0.08
    엇
    -0.08
    .gdx
    -0.07
     augue
    -0.07
    izing
    -0.07
    -0.07
    ющая
    -0.07
     смартф
    -0.07
    gende
    -0.07
    Sb
    -0.07
    POSITIVE LOGITS
    M
    0.14
    F
    0.11
    Μ
    0.09
    V
    0.09
    K
    0.09
    Fy
    0.09
    MV
    0.08
    igeria
    0.08
    LW
    0.08
    MN
    0.08
    Activations Density 0.005%

    No Known Activations