© 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. 19-RESID-POST-AA
    11. 103553
    Prev
    Next
    INDEX
    Explanations

    or

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contingent
    -0.07
    -tal
    -0.07
     kertoo
    -0.07
     imminent
    -0.07
     genes
    -0.07
    _employee
    -0.07
     employer
    -0.07
    妹妹
    -0.07
    ослов
    -0.07
     now
    -0.07
    POSITIVE LOGITS
    »:↵↵
    0.08
     permit
    0.08
     পুরো
    0.08
    atitis
    0.08
    ALLOW
    0.07
    时期
    0.07
     straighten
    0.07
     overal
    0.07
    後
    0.07
     শুধু
    0.07
    Activations Density 0.000%

    No Known Activations