© 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. 75737
    Prev
    Next
    INDEX
    Explanations

    reading glasses

    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
     vapor
    -0.08
    .obtener
    -0.08
     Kapoor
    -0.08
    .days
    -0.08
    .events
    -0.08
    ימים
    -0.08
     vamp
    -0.08
     terv
    -0.08
     vap
    -0.07
     evapor
    -0.07
    POSITIVE LOGITS
    ifting
    0.09
    wise
    0.09
    aptops
    0.08
     cò
    0.08
    _stat
    0.08
    ilie
    0.08
    Viewing
    0.07
    noinspection
    0.07
     cujo
    0.07
     toepassingen
    0.07
    Activations Density 0.006%

    No Known Activations