© 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. 97811
    Prev
    Next
    INDEX
    Explanations

    Variations

    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
     portion
    -0.08
    defaults
    -0.08
     maioria
    -0.08
     plupart
    -0.08
     layer
    -0.08
     gedeelte
    -0.08
     ذریعہ
    -0.08
    relay
    -0.08
     کے
    -0.07
     nodes
    -0.07
    POSITIVE LOGITS
    变
    0.28
    變
    0.26
     변
    0.25
    変
    0.22
     válto
    0.20
    _vari
    0.20
     വക
    0.20
     variantes
    0.19
     Vari
    0.19
     biến
    0.19
    Activations Density 0.017%

    No Known Activations