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. 7-RESID-POST-AA
    6. 130985
    Prev
    Next
    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bugs
    -0.08
     bugs
    -0.08
     motion
    -0.08
     Alb
    -0.07
     Richards
    -0.07
     Motion
    -0.07
    _DEL
    -0.07
     requisite
    -0.07
     ಮುಖ್ಯ
    -0.07
     beta
    -0.07
    POSITIVE LOGITS
    gzip
    0.08
    _gp
    0.08
    üge
    0.08
    IPE
    0.08
    ipe
    0.08
     내가
    0.08
     أنه
    0.08
    Institute
    0.08
     گروه
    0.07
    -hide
    0.07
    Activations Density 0.000%

    No Known Activations