© 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. 19-RESID-POST-AA
    11. 103560
    Prev
    Next
    INDEX
    Explanations

    compatibility

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEF
    -0.07
     thief
    -0.07
    @Setter
    -0.07
     získ
    -0.07
    جراءات
    -0.07
     replen
    -0.07
     elaboração
    -0.07
    'arrivée
    -0.07
    ဲ
    -0.07
    ริง
    -0.07
    POSITIVE LOGITS
     compatibility
    0.43
     Compatibility
    0.40
    Compatibility
    0.39
     kompat
    0.37
    compat
    0.36
     compat
    0.35
     compatible
    0.34
     Compat
    0.34
     compatibles
    0.33
    兼
    0.32
    Activations Density 0.105%

    No Known Activations