© 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. 11-RESID-POST-AA
    11. 112692
    Prev
    Next
    INDEX
    Explanations

    expand text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intersection
    -0.08
     cle
    -0.08
     Mathieu
    -0.07
    _usb
    -0.07
    _prec
    -0.07
     û
    -0.07
     swift
    -0.07
     Hel
    -0.07
     atl
    -0.07
     streamlined
    -0.07
    POSITIVE LOGITS
    扩
    0.12
     uitbre
    0.11
     expands
    0.11
     verläng
    0.11
    増
    0.11
    扩大
    0.10
     expansions
    0.10
     Expand
    0.10
     расшир
    0.10
     увеличить
    0.10
    Activations Density 0.007%

    No Known Activations