© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50115
    Prev
    Next
    INDEX
    Explanations

    �

    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
    Ascending
    -0.08
    .lst
    -0.08
     ascending
    -0.08
    isem
    -0.08
    iseconds
    -0.08
    txn
    -0.08
    қиқ
    -0.08
    PRIMARY
    -0.08
    chnung
    -0.07
     chiffre
    -0.07
    POSITIVE LOGITS
    ram
    0.08
     asylum
    0.08
    �
    0.07
    ৌ
    0.07
    百度
    0.07
    ૌ
    0.07
     ACM
    0.07
     рын
    0.07
    手机
    0.07
     모바일
    0.07
    Activations Density 0.001%

    No Known Activations