© 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. 103193
    Prev
    Next
    INDEX
    Explanations

    increase

    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
    hangi
    -0.10
    telling
    -0.10
    yeed
    -0.09
    giver
    -0.09
    esthetic
    -0.09
    taken
    -0.09
    most
    -0.09
    istic
    -0.09
    īg
    -0.09
    isme
    -0.09
    POSITIVE LOGITS
    /de
    0.20
     trưởng
    0.11
     dramatically
    0.10
     substantially
    0.09
    ,de
    0.09
    /el
    0.09
     یافته
    0.09
    /delete
    0.08
     drastically
    0.08
     complexity
    0.08
    Activations Density 0.046%

    No Known Activations