© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 49130
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
     pers
    -0.09
     मौ
    -0.08
    Pers
    -0.08
     TO
    -0.07
     shaders
    -0.07
    _SCRIPT
    -0.07
    Persistence
    -0.07
    ाका
    -0.07
    (string
    -0.07
     persistence
    -0.07
    POSITIVE LOGITS
    ysg
    0.08
    -Ch
    0.08
     Заб
    0.08
     చేసింది
    0.08
     Nicht
    0.08
     Зав
    0.08
     nch
    0.08
     overwinning
    0.08
     Ett
    0.08
     Wolfgang
    0.08
    Activations Density 0.006%

    No Known Activations