© 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. 11-RESID-POST-AA
    11. 64830
    Prev
    Next
    INDEX
    Explanations

    or

    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
     hohe
    -0.08
     ವಿವರ
    -0.08
    .Destroy
    -0.08
     locale
    -0.08
    .Caption
    -0.08
     Locale
    -0.08
    ,),
    -0.08
    locale
    -0.08
     Barnes
    -0.08
     Fischer
    -0.08
    POSITIVE LOGITS
     whichever
    0.12
    任选
    0.11
     preferably
    0.10
    之一
    0.10
    Either
    0.09
     chosen
    0.09
    ≤
    0.09
     પસંદ
    0.09
     either
    0.09
     ഏത
    0.09
    Activations Density 0.080%

    No Known Activations