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

    Neuronpedia

    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. 5429
    Prev
    Next
    INDEX
    Explanations

    تق

    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
     proposent
    -0.08
     വിട്ട
    -0.08
     möjligt
    -0.08
     drinken
    -0.07
    iqué
    -0.07
    tiin
    -0.07
    방
    -0.07
     Ping
    -0.07
     mesaj
    -0.07
     сообщения
    -0.07
    POSITIVE LOGITS
    صد
    0.11
    ص
    0.09
    �
    0.09
    暑
    0.08
     SMB
    0.08
    fog
    0.08
     tranche
    0.08
     Jov
    0.07
    .ptr
    0.07
     residency
    0.07
    Activations Density 0.001%

    No Known Activations