© 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. 50158
    Prev
    Next
    INDEX
    Explanations

    susp

    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
     grilling
    -0.09
    있
    -0.09
     thriller
    -0.08
     확보
    -0.08
     məhs
    -0.08
    ÜR
    -0.08
    YE
    -0.08
    สินค้า
    -0.08
    rı
    -0.08
     מוצר
    -0.08
    POSITIVE LOGITS
    ensions
    0.14
    icious
    0.13
    ending
    0.12
    ension
    0.11
    ensiones
    0.11
    ended
    0.10
    ensión
    0.10
    icion
    0.10
    ends
    0.10
    icions
    0.10
    Activations Density 0.004%

    No Known Activations