© 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. 102153
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
     quantified
    -0.09
    _losses
    -0.09
     алғашқы
    -0.08
    ihen
    -0.08
     losses
    -0.08
    τική
    -0.08
     benodigde
    -0.08
     Aktual
    -0.08
    	initial
    -0.08
     Änder
    -0.08
    POSITIVE LOGITS
     grandeur
    0.08
     andra
    0.08
     conservation
    0.08
     prevention
    0.08
     anderen
    0.08
     other
    0.08
     generale
    0.08
     دیگر
    0.07
     others
    0.07
     grands
    0.07
    Activations Density 0.010%

    No Known Activations