© 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. 23-RESID-POST-AA
    11. 96396
    Prev
    Next
    INDEX
    Explanations

    he

    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
     मा
    -0.08
     maut
    -0.08
    Ạ
    -0.07
    ματο
    -0.07
    .One
    -0.07
     println
    -0.07
     Fy
    -0.07
    _OF
    -0.07
     konfl
    -0.07
    Of
    -0.07
    POSITIVE LOGITS
    vel
    0.15
    ve
    0.14
    arten
    0.12
    VEL
    0.11
    VE
    0.10
    velse
    0.10
    .vel
    0.10
    Vel
    0.09
     Vel
    0.09
    _vel
    0.08
    Activations Density 0.000%

    No Known Activations