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. 130750
    Prev
    Next
    INDEX
    Explanations

    pref

    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
    acji
    -0.09
    ysa
    -0.08
     ذ
    -0.08
    قلة
    -0.08
     anul
    -0.08
    jord
    -0.07
    acyj
    -0.07
     qen
    -0.07
     underwent
    -0.07
    jaz
    -0.07
    POSITIVE LOGITS
    abs
    0.09
    ാബ
    0.09
    inished
    0.09
    ેબ
    0.08
    াবে
    0.08
    ాబు
    0.08
    ab
    0.08
     abs
    0.08
    abric
    0.08
    ాబ
    0.08
    Activations Density 0.001%

    No Known Activations