© 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. 6464
    Prev
    Next
    INDEX
    Explanations

    f

    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
    agad
    -0.08
    ization
    -0.08
     nightlife
    -0.07
    led
    -0.07
    Academ
    -0.07
     genesis
    -0.07
    .DIS
    -0.07
    eer
    -0.07
    /app
    -0.07
    isation
    -0.07
    POSITIVE LOGITS
    ired
    0.09
    ából
    0.09
    ाटक
    0.08
    унда
    0.08
    ાયર
    0.08
    ire
    0.08
    ায়
    0.08
    ಸ
    0.08
    াস
    0.08
    ायर
    0.08
    Activations Density 0.005%

    No Known Activations