© 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. 49553
    Prev
    Next
    INDEX
    Explanations

    t

    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
     Ky
    -0.08
    াশি
    -0.08
    羞
    -0.08
     Merci
    -0.08
    алин
    -0.08
     culpa
    -0.08
     У
    -0.08
     Gunnar
    -0.08
    ಾಲ್
    -0.08
     Але
    -0.08
    POSITIVE LOGITS
     dto
    0.07
     behalf
    0.07
    Fax
    0.07
     upload
    0.07
     rg
    0.07
     ai
    0.07
     ii
    0.07
    qc
    0.07
    λ
    0.07
    enom
    0.07
    Activations Density 0.000%

    No Known Activations